Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3602 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1871. Min Range: -7.1871
Max Act: 7.1871. Min Act: -0.1700
Data Index: 4888524 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1871. Min Range: -7.1871
Max Act: 7.0934. Min Act: -0.1700
Data Index: 5983711 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1871. Min Range: -7.1871
Max Act: 7.0309. Min Act: -0.1700
Data Index: 8333881 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1871. Min Range: -7.1871
Max Act: 6.7809. Min Act: -0.1700
Data Index: 1472662 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1871. Min Range: -7.1871
Max Act: 6.7496. Min Act: -0.1700
Data Index: 2959718 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1871. Min Range: -7.1871
Max Act: 6.7496. Min Act: -0.1700
Data Index: 1401573 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1871. Min Range: -7.1871
Max Act: 6.7496. Min Act: -0.1700
Data Index: 5253699 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1871. Min Range: -7.1871
Max Act: 6.7184. Min Act: -0.1700
Data Index: 1855131 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1871. Min Range: -7.1871
Max Act: 6.7184. Min Act: -0.1700
Data Index: 229626 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1871. Min Range: -7.1871
Max Act: 6.6559. Min Act: -0.1700
Data Index: 6351332 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1871. Min Range: -7.1871
Max Act: 6.6559. Min Act: -0.1700
Data Index: 2348518 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1871. Min Range: -7.1871
Max Act: 6.6246. Min Act: -0.1700
Data Index: 6080630 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1871. Min Range: -7.1871
Max Act: 6.5934. Min Act: -0.1700
Data Index: 5202316 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1871. Min Range: -7.1871
Max Act: 6.6246. Min Act: -0.1700
Data Index: 4414319 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1871. Min Range: -7.1871
Max Act: 6.5621. Min Act: -0.1700
Data Index: 7489011 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1871. Min Range: -7.1871
Max Act: 6.5309. Min Act: -0.1700
Data Index: 3601301 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1871. Min Range: -7.1871
Max Act: 6.5621. Min Act: -0.1700
Data Index: 576690 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1871. Min Range: -7.1871
Max Act: 6.5309. Min Act: -0.1700
Data Index: 1979767 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1871. Min Range: -7.1871
Max Act: 6.5309. Min Act: -0.1700
Data Index: 8279932 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1871. Min Range: -7.1871
Max Act: 6.4996. Min Act: -0.1700
Data Index: 1047251 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19