Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3841 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6265. Min Range: -4.6265
Max Act: 4.6265. Min Act: -0.1700
Data Index: 5100708 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6265. Min Range: -4.6265
Max Act: 4.2828. Min Act: -0.1700
Data Index: 6493906 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6265. Min Range: -4.6265
Max Act: 4.2515. Min Act: -0.1700
Data Index: 3768056 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6265. Min Range: -4.6265
Max Act: 4.1890. Min Act: -0.1700
Data Index: 2177161 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6265. Min Range: -4.6265
Max Act: 4.1265. Min Act: -0.1700
Data Index: 1342236 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6265. Min Range: -4.6265
Max Act: 4.0640. Min Act: -0.1700
Data Index: 895451 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6265. Min Range: -4.6265
Max Act: 4.0327. Min Act: -0.1700
Data Index: 2138392 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6265. Min Range: -4.6265
Max Act: 4.0327. Min Act: -0.1700
Data Index: 6058927 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6265. Min Range: -4.6265
Max Act: 4.0014. Min Act: -0.1700
Data Index: 5143700 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6265. Min Range: -4.6265
Max Act: 4.0640. Min Act: -0.1700
Data Index: 3327816 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6265. Min Range: -4.6265
Max Act: 4.0327. Min Act: -0.1700
Data Index: 4733764 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6265. Min Range: -4.6265
Max Act: 4.0014. Min Act: -0.1700
Data Index: 2059481 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6265. Min Range: -4.6265
Max Act: 4.0014. Min Act: -0.1700
Data Index: 7211666 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6265. Min Range: -4.6265
Max Act: 4.0327. Min Act: -0.1700
Data Index: 4963169 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6265. Min Range: -4.6265
Max Act: 4.0014. Min Act: -0.1700
Data Index: 490708 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6265. Min Range: -4.6265
Max Act: 3.9702. Min Act: -0.1700
Data Index: 4208158 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6265. Min Range: -4.6265
Max Act: 4.0014. Min Act: -0.1700
Data Index: 3685623 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6265. Min Range: -4.6265
Max Act: 3.9077. Min Act: -0.1700
Data Index: 7981922 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6265. Min Range: -4.6265
Max Act: 3.9389. Min Act: -0.1700
Data Index: 7871376 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6265. Min Range: -4.6265
Max Act: 3.9077. Min Act: -0.1700
Data Index: 1221923 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19