Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2460 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7903. Min Range: -5.7903
Max Act: 5.7903. Min Act: -0.1700
Data Index: 1606098 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7903. Min Range: -5.7903
Max Act: 5.7278. Min Act: -0.1700
Data Index: 725530 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7903. Min Range: -5.7903
Max Act: 5.6653. Min Act: -0.1700
Data Index: 6069798 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7903. Min Range: -5.7903
Max Act: 5.6028. Min Act: -0.1700
Data Index: 7529190 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7903. Min Range: -5.7903
Max Act: 5.4465. Min Act: -0.1700
Data Index: 2717203 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7903. Min Range: -5.7903
Max Act: 5.4778. Min Act: -0.1700
Data Index: 3549168 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7903. Min Range: -5.7903
Max Act: 5.3840. Min Act: -0.1700
Data Index: 798358 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7903. Min Range: -5.7903
Max Act: 5.4465. Min Act: -0.1700
Data Index: 7448949 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7903. Min Range: -5.7903
Max Act: 5.3840. Min Act: -0.1700
Data Index: 6312268 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7903. Min Range: -5.7903
Max Act: 5.3840. Min Act: -0.1700
Data Index: 2550072 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7903. Min Range: -5.7903
Max Act: 5.4153. Min Act: -0.1700
Data Index: 4793482 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7903. Min Range: -5.7903
Max Act: 5.3528. Min Act: -0.1700
Data Index: 5110993 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7903. Min Range: -5.7903
Max Act: 5.3215. Min Act: -0.1700
Data Index: 5266699 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7903. Min Range: -5.7903
Max Act: 5.3528. Min Act: -0.1700
Data Index: 2265091 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7903. Min Range: -5.7903
Max Act: 5.2903. Min Act: -0.1700
Data Index: 1063724 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7903. Min Range: -5.7903
Max Act: 5.2590. Min Act: -0.1700
Data Index: 7281857 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7903. Min Range: -5.7903
Max Act: 5.2278. Min Act: -0.1700
Data Index: 180032 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7903. Min Range: -5.7903
Max Act: 5.2590. Min Act: -0.1700
Data Index: 2784144 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7903. Min Range: -5.7903
Max Act: 5.2903. Min Act: -0.1700
Data Index: 2904318 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7903. Min Range: -5.7903
Max Act: 5.2590. Min Act: -0.1700
Data Index: 5443189 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19