Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2445 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5472. Min Range: -6.5472
Max Act: 6.5472. Min Act: -0.1700
Data Index: 5254272 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5472. Min Range: -6.5472
Max Act: 6.2035. Min Act: -0.1700
Data Index: 5829607 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5472. Min Range: -6.5472
Max Act: 6.0785. Min Act: -0.1700
Data Index: 1925003 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5472. Min Range: -6.5472
Max Act: 6.0472. Min Act: -0.1700
Data Index: 8589614 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5472. Min Range: -6.5472
Max Act: 6.0472. Min Act: -0.1700
Data Index: 1696688 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5472. Min Range: -6.5472
Max Act: 6.0160. Min Act: -0.1700
Data Index: 6469280 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5472. Min Range: -6.5472
Max Act: 5.9535. Min Act: -0.1700
Data Index: 5800930 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5472. Min Range: -6.5472
Max Act: 5.8910. Min Act: -0.1700
Data Index: 3558356 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5472. Min Range: -6.5472
Max Act: 5.8910. Min Act: -0.1700
Data Index: 8245734 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5472. Min Range: -6.5472
Max Act: 5.8910. Min Act: -0.1700
Data Index: 1507248 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5472. Min Range: -6.5472
Max Act: 5.8910. Min Act: -0.1700
Data Index: 6145775 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5472. Min Range: -6.5472
Max Act: 5.8597. Min Act: -0.1700
Data Index: 3855500 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5472. Min Range: -6.5472
Max Act: 5.8597. Min Act: -0.1700
Data Index: 8585718 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5472. Min Range: -6.5472
Max Act: 5.8285. Min Act: -0.1700
Data Index: 3268334 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5472. Min Range: -6.5472
Max Act: 5.7972. Min Act: -0.1700
Data Index: 3575921 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5472. Min Range: -6.5472
Max Act: 5.7660. Min Act: -0.1700
Data Index: 3933579 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5472. Min Range: -6.5472
Max Act: 5.7972. Min Act: -0.1700
Data Index: 6980432 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5472. Min Range: -6.5472
Max Act: 5.7972. Min Act: -0.1700
Data Index: 2824067 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5472. Min Range: -6.5472
Max Act: 5.7660. Min Act: -0.1700
Data Index: 1905182 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5472. Min Range: -6.5472
Max Act: 5.7347. Min Act: -0.1700
Data Index: 7688796 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19