Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1056 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6445. Min Range: -5.6445
Max Act: 5.6445. Min Act: -0.1700
Data Index: 8558432 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6445. Min Range: -5.6445
Max Act: 5.5507. Min Act: -0.1700
Data Index: 908065 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6445. Min Range: -5.6445
Max Act: 5.4570. Min Act: -0.1700
Data Index: 6932151 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6445. Min Range: -5.6445
Max Act: 5.4570. Min Act: -0.1700
Data Index: 5195204 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6445. Min Range: -5.6445
Max Act: 5.4257. Min Act: -0.1700
Data Index: 6675628 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6445. Min Range: -5.6445
Max Act: 5.3945. Min Act: -0.1700
Data Index: 5861900 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6445. Min Range: -5.6445
Max Act: 5.4257. Min Act: -0.1700
Data Index: 7940002 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6445. Min Range: -5.6445
Max Act: 5.4257. Min Act: -0.1700
Data Index: 8298834 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6445. Min Range: -5.6445
Max Act: 5.3945. Min Act: -0.1700
Data Index: 1178215 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6445. Min Range: -5.6445
Max Act: 5.3945. Min Act: -0.1700
Data Index: 6227806 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6445. Min Range: -5.6445
Max Act: 5.3945. Min Act: -0.1700
Data Index: 2930317 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6445. Min Range: -5.6445
Max Act: 5.3320. Min Act: -0.1700
Data Index: 5049475 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6445. Min Range: -5.6445
Max Act: 5.3632. Min Act: -0.1700
Data Index: 6614321 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6445. Min Range: -5.6445
Max Act: 5.3632. Min Act: -0.1700
Data Index: 1801255 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6445. Min Range: -5.6445
Max Act: 5.3632. Min Act: -0.1700
Data Index: 6125749 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6445. Min Range: -5.6445
Max Act: 5.3007. Min Act: -0.1700
Data Index: 8241587 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6445. Min Range: -5.6445
Max Act: 5.3007. Min Act: -0.1700
Data Index: 1596528 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6445. Min Range: -5.6445
Max Act: 5.3007. Min Act: -0.1700
Data Index: 1652210 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6445. Min Range: -5.6445
Max Act: 5.3007. Min Act: -0.1700
Data Index: 2383265 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6445. Min Range: -5.6445
Max Act: 5.2695. Min Act: -0.1700
Data Index: 7189793 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19