Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 203 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 14.2390. Min Range: -14.2390
Max Act: 14.2390. Min Act: -0.1700
Data Index: 4800305 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.2390. Min Range: -14.2390
Max Act: 14.0515. Min Act: -0.1700
Data Index: 3582655 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.2390. Min Range: -14.2390
Max Act: 13.9890. Min Act: -0.1700
Data Index: 243275 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.2390. Min Range: -14.2390
Max Act: 13.8015. Min Act: -0.1700
Data Index: 248377 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.2390. Min Range: -14.2390
Max Act: 13.8640. Min Act: -0.1700
Data Index: 3357525 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.2390. Min Range: -14.2390
Max Act: 13.8640. Min Act: -0.1700
Data Index: 6964242 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.2390. Min Range: -14.2390
Max Act: 13.8015. Min Act: -0.1700
Data Index: 793946 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.2390. Min Range: -14.2390
Max Act: 13.8015. Min Act: -0.1700
Data Index: 7400507 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.2390. Min Range: -14.2390
Max Act: 13.8015. Min Act: -0.1700
Data Index: 5922851 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.2390. Min Range: -14.2390
Max Act: 13.7390. Min Act: -0.1700
Data Index: 1028741 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.2390. Min Range: -14.2390
Max Act: 13.8640. Min Act: -0.1700
Data Index: 2373133 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.2390. Min Range: -14.2390
Max Act: 13.7390. Min Act: -0.1700
Data Index: 2150661 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.2390. Min Range: -14.2390
Max Act: 13.6765. Min Act: -0.1700
Data Index: 6095751 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.2390. Min Range: -14.2390
Max Act: 13.8015. Min Act: -0.1700
Data Index: 3104263 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.2390. Min Range: -14.2390
Max Act: 13.4890. Min Act: -0.1700
Data Index: 3215104 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.2390. Min Range: -14.2390
Max Act: 13.6765. Min Act: -0.1700
Data Index: 6762581 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.2390. Min Range: -14.2390
Max Act: 13.6140. Min Act: -0.1700
Data Index: 1157316 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.2390. Min Range: -14.2390
Max Act: 13.6140. Min Act: -0.1700
Data Index: 528597 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.2390. Min Range: -14.2390
Max Act: 13.6765. Min Act: -0.1700
Data Index: 2013521 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.2390. Min Range: -14.2390
Max Act: 13.6765. Min Act: -0.1700
Data Index: 6245117 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19