Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2781 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9348. Min Range: -7.9348
Max Act: 7.9348. Min Act: -0.1700
Data Index: 5956410 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9348. Min Range: -7.9348
Max Act: 7.8098. Min Act: -0.1700
Data Index: 2384466 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9348. Min Range: -7.9348
Max Act: 7.6535. Min Act: -0.1700
Data Index: 7579138 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9348. Min Range: -7.9348
Max Act: 7.4973. Min Act: -0.1700
Data Index: 5464251 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9348. Min Range: -7.9348
Max Act: 7.4973. Min Act: -0.1700
Data Index: 7931222 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9348. Min Range: -7.9348
Max Act: 7.4035. Min Act: -0.1700
Data Index: 6572211 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9348. Min Range: -7.9348
Max Act: 7.3723. Min Act: -0.1700
Data Index: 3926168 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9348. Min Range: -7.9348
Max Act: 7.3410. Min Act: -0.1700
Data Index: 5463084 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9348. Min Range: -7.9348
Max Act: 7.2473. Min Act: -0.1700
Data Index: 5854392 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9348. Min Range: -7.9348
Max Act: 7.2160. Min Act: -0.1700
Data Index: 1004174 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9348. Min Range: -7.9348
Max Act: 7.2473. Min Act: -0.1700
Data Index: 7595825 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9348. Min Range: -7.9348
Max Act: 7.2473. Min Act: -0.1700
Data Index: 8773902 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9348. Min Range: -7.9348
Max Act: 7.1848. Min Act: -0.1700
Data Index: 4425776 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9348. Min Range: -7.9348
Max Act: 7.1848. Min Act: -0.1700
Data Index: 6464091 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9348. Min Range: -7.9348
Max Act: 7.1535. Min Act: -0.1700
Data Index: 7912451 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9348. Min Range: -7.9348
Max Act: 7.1535. Min Act: -0.1700
Data Index: 4967927 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9348. Min Range: -7.9348
Max Act: 7.1223. Min Act: -0.1700
Data Index: 1604829 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9348. Min Range: -7.9348
Max Act: 7.1223. Min Act: -0.1700
Data Index: 3080895 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9348. Min Range: -7.9348
Max Act: 7.1223. Min Act: -0.1700
Data Index: 1522277 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9348. Min Range: -7.9348
Max Act: 7.1223. Min Act: -0.1700
Data Index: 5593808 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19