Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 661 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1791. Min Range: -6.1791
Max Act: 6.1791. Min Act: -0.1700
Data Index: 943793 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1791. Min Range: -6.1791
Max Act: 6.0229. Min Act: -0.1700
Data Index: 5375537 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1791. Min Range: -6.1791
Max Act: 6.0229. Min Act: -0.1700
Data Index: 3727919 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1791. Min Range: -6.1791
Max Act: 5.9916. Min Act: -0.1700
Data Index: 1078569 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1791. Min Range: -6.1791
Max Act: 5.8666. Min Act: -0.1700
Data Index: 5696989 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1791. Min Range: -6.1791
Max Act: 5.7416. Min Act: -0.1700
Data Index: 7930924 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1791. Min Range: -6.1791
Max Act: 5.7416. Min Act: -0.1700
Data Index: 7922404 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1791. Min Range: -6.1791
Max Act: 5.6479. Min Act: -0.1700
Data Index: 4668142 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1791. Min Range: -6.1791
Max Act: 5.5854. Min Act: -0.1700
Data Index: 8744174 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1791. Min Range: -6.1791
Max Act: 5.5541. Min Act: -0.1700
Data Index: 7349720 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1791. Min Range: -6.1791
Max Act: 5.4916. Min Act: -0.1700
Data Index: 5977417 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1791. Min Range: -6.1791
Max Act: 5.4604. Min Act: -0.1700
Data Index: 7765108 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1791. Min Range: -6.1791
Max Act: 5.4604. Min Act: -0.1700
Data Index: 5736044 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1791. Min Range: -6.1791
Max Act: 5.4291. Min Act: -0.1700
Data Index: 3029603 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1791. Min Range: -6.1791
Max Act: 5.4291. Min Act: -0.1700
Data Index: 5253534 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1791. Min Range: -6.1791
Max Act: 5.3979. Min Act: -0.1700
Data Index: 8268266 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1791. Min Range: -6.1791
Max Act: 5.4291. Min Act: -0.1700
Data Index: 4456246 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1791. Min Range: -6.1791
Max Act: 5.3979. Min Act: -0.1700
Data Index: 6183814 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1791. Min Range: -6.1791
Max Act: 5.3979. Min Act: -0.1700
Data Index: 3934597 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1791. Min Range: -6.1791
Max Act: 5.3979. Min Act: -0.1700
Data Index: 6167900 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19