Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 290 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3416. Min Range: -6.3416
Max Act: 6.3416. Min Act: -0.1700
Data Index: 3566284 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3416. Min Range: -6.3416
Max Act: 6.3416. Min Act: -0.1700
Data Index: 3691276 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3416. Min Range: -6.3416
Max Act: 6.0916. Min Act: -0.1700
Data Index: 4163674 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3416. Min Range: -6.3416
Max Act: 6.0916. Min Act: -0.1700
Data Index: 4298841 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3416. Min Range: -6.3416
Max Act: 6.0603. Min Act: -0.1700
Data Index: 826240 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3416. Min Range: -6.3416
Max Act: 6.0603. Min Act: -0.1700
Data Index: 3131805 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3416. Min Range: -6.3416
Max Act: 5.9666. Min Act: -0.1700
Data Index: 361210 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3416. Min Range: -6.3416
Max Act: 5.9666. Min Act: -0.1700
Data Index: 2715080 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3416. Min Range: -6.3416
Max Act: 5.9353. Min Act: -0.1700
Data Index: 4757244 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3416. Min Range: -6.3416
Max Act: 5.8728. Min Act: -0.1700
Data Index: 6497493 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3416. Min Range: -6.3416
Max Act: 5.8728. Min Act: -0.1700
Data Index: 4797474 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3416. Min Range: -6.3416
Max Act: 5.9041. Min Act: -0.1700
Data Index: 4420357 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3416. Min Range: -6.3416
Max Act: 5.9041. Min Act: -0.1700
Data Index: 7565946 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3416. Min Range: -6.3416
Max Act: 5.8728. Min Act: -0.1700
Data Index: 6791643 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3416. Min Range: -6.3416
Max Act: 5.8416. Min Act: -0.1700
Data Index: 5551622 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3416. Min Range: -6.3416
Max Act: 5.8103. Min Act: -0.1700
Data Index: 5806161 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3416. Min Range: -6.3416
Max Act: 5.7791. Min Act: -0.1700
Data Index: 5768693 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3416. Min Range: -6.3416
Max Act: 5.7791. Min Act: -0.1700
Data Index: 5361016 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3416. Min Range: -6.3416
Max Act: 5.8103. Min Act: -0.1700
Data Index: 6406971 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3416. Min Range: -6.3416
Max Act: 5.7166. Min Act: -0.1700
Data Index: 5806159 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #19