Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5097 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3680. Min Range: -5.3680
Max Act: 5.3680. Min Act: -0.1700
Data Index: 3577623 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3680. Min Range: -5.3680
Max Act: 5.3368. Min Act: -0.1700
Data Index: 3306650 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3680. Min Range: -5.3680
Max Act: 5.3368. Min Act: -0.1700
Data Index: 4464480 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3680. Min Range: -5.3680
Max Act: 5.3055. Min Act: -0.1700
Data Index: 1001720 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3680. Min Range: -5.3680
Max Act: 5.3055. Min Act: -0.1700
Data Index: 4116784 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3680. Min Range: -5.3680
Max Act: 5.2118. Min Act: -0.1700
Data Index: 3977674 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3680. Min Range: -5.3680
Max Act: 5.2430. Min Act: -0.1700
Data Index: 7499140 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3680. Min Range: -5.3680
Max Act: 5.2118. Min Act: -0.1700
Data Index: 3977670 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3680. Min Range: -5.3680
Max Act: 5.1805. Min Act: -0.1700
Data Index: 6671212 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3680. Min Range: -5.3680
Max Act: 5.1805. Min Act: -0.1700
Data Index: 5724478 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3680. Min Range: -5.3680
Max Act: 5.1493. Min Act: -0.1700
Data Index: 6172087 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3680. Min Range: -5.3680
Max Act: 5.1493. Min Act: -0.1700
Data Index: 2904628 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3680. Min Range: -5.3680
Max Act: 5.1180. Min Act: -0.1700
Data Index: 8171529 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3680. Min Range: -5.3680
Max Act: 5.0868. Min Act: -0.1700
Data Index: 6410433 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3680. Min Range: -5.3680
Max Act: 5.0868. Min Act: -0.1700
Data Index: 7204244 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3680. Min Range: -5.3680
Max Act: 5.0868. Min Act: -0.1700
Data Index: 472054 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3680. Min Range: -5.3680
Max Act: 5.0868. Min Act: -0.1700
Data Index: 8589268 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3680. Min Range: -5.3680
Max Act: 5.0555. Min Act: -0.1700
Data Index: 1523985 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3680. Min Range: -5.3680
Max Act: 5.0243. Min Act: -0.1700
Data Index: 304009 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3680. Min Range: -5.3680
Max Act: 5.0555. Min Act: -0.1700
Data Index: 2853339 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19