Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 594 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8293. Min Range: -6.8293
Max Act: 6.8293. Min Act: -0.1700
Data Index: 8423274 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8293. Min Range: -6.8293
Max Act: 6.7668. Min Act: -0.1700
Data Index: 6289170 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8293. Min Range: -6.8293
Max Act: 6.7668. Min Act: -0.1700
Data Index: 1860798 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8293. Min Range: -6.8293
Max Act: 6.7356. Min Act: -0.1700
Data Index: 6205437 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8293. Min Range: -6.8293
Max Act: 6.7043. Min Act: -0.1700
Data Index: 927042 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8293. Min Range: -6.8293
Max Act: 6.6418. Min Act: -0.1700
Data Index: 996248 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8293. Min Range: -6.8293
Max Act: 6.6731. Min Act: -0.1700
Data Index: 49666 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8293. Min Range: -6.8293
Max Act: 6.6106. Min Act: -0.1700
Data Index: 3582837 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8293. Min Range: -6.8293
Max Act: 6.6106. Min Act: -0.1700
Data Index: 493488 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8293. Min Range: -6.8293
Max Act: 6.5481. Min Act: -0.1700
Data Index: 3964324 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8293. Min Range: -6.8293
Max Act: 6.5168. Min Act: -0.1700
Data Index: 3090079 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8293. Min Range: -6.8293
Max Act: 6.4856. Min Act: -0.1700
Data Index: 97480 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8293. Min Range: -6.8293
Max Act: 6.4856. Min Act: -0.1700
Data Index: 8793826 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8293. Min Range: -6.8293
Max Act: 6.4856. Min Act: -0.1700
Data Index: 609979 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8293. Min Range: -6.8293
Max Act: 6.4543. Min Act: -0.1700
Data Index: 2974980 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8293. Min Range: -6.8293
Max Act: 6.4543. Min Act: -0.1700
Data Index: 4415964 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8293. Min Range: -6.8293
Max Act: 6.4231. Min Act: -0.1700
Data Index: 2919039 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8293. Min Range: -6.8293
Max Act: 6.4231. Min Act: -0.1700
Data Index: 1327850 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8293. Min Range: -6.8293
Max Act: 6.3918. Min Act: -0.1700
Data Index: 3068410 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8293. Min Range: -6.8293
Max Act: 6.4231. Min Act: -0.1700
Data Index: 8322498 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19