Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 856 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1472. Min Range: -6.1472
Max Act: 6.1472. Min Act: -0.1700
Data Index: 8741936 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1472. Min Range: -6.1472
Max Act: 6.1472. Min Act: -0.1700
Data Index: 2159891 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1472. Min Range: -6.1472
Max Act: 5.8347. Min Act: -0.1700
Data Index: 7910692 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1472. Min Range: -6.1472
Max Act: 5.7722. Min Act: -0.1700
Data Index: 8226548 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1472. Min Range: -6.1472
Max Act: 5.7097. Min Act: -0.1700
Data Index: 4397964 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1472. Min Range: -6.1472
Max Act: 5.7722. Min Act: -0.1700
Data Index: 3695576 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1472. Min Range: -6.1472
Max Act: 5.7409. Min Act: -0.1700
Data Index: 3471102 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1472. Min Range: -6.1472
Max Act: 5.7722. Min Act: -0.1700
Data Index: 194775 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1472. Min Range: -6.1472
Max Act: 5.7097. Min Act: -0.1700
Data Index: 6266444 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1472. Min Range: -6.1472
Max Act: 5.7097. Min Act: -0.1700
Data Index: 6607995 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1472. Min Range: -6.1472
Max Act: 5.6784. Min Act: -0.1700
Data Index: 627017 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1472. Min Range: -6.1472
Max Act: 5.6472. Min Act: -0.1700
Data Index: 2654653 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1472. Min Range: -6.1472
Max Act: 5.6784. Min Act: -0.1700
Data Index: 205014 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1472. Min Range: -6.1472
Max Act: 5.6159. Min Act: -0.1700
Data Index: 1762335 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1472. Min Range: -6.1472
Max Act: 5.6472. Min Act: -0.1700
Data Index: 4473722 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1472. Min Range: -6.1472
Max Act: 5.6159. Min Act: -0.1700
Data Index: 1212260 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1472. Min Range: -6.1472
Max Act: 5.6159. Min Act: -0.1700
Data Index: 6268194 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1472. Min Range: -6.1472
Max Act: 5.5847. Min Act: -0.1700
Data Index: 5703153 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1472. Min Range: -6.1472
Max Act: 5.5534. Min Act: -0.1700
Data Index: 786555 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1472. Min Range: -6.1472
Max Act: 5.5847. Min Act: -0.1700
Data Index: 6336489 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19