Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1178 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8228. Min Range: -2.8228
Max Act: 2.8228. Min Act: -0.1700
Data Index: 6332215 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8228. Min Range: -2.8228
Max Act: 2.8069. Min Act: -0.1700
Data Index: 3080987 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8228. Min Range: -2.8228
Max Act: 2.7432. Min Act: -0.1700
Data Index: 5088347 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8228. Min Range: -2.8228
Max Act: 2.7432. Min Act: -0.1700
Data Index: 7792100 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8228. Min Range: -2.8228
Max Act: 2.7432. Min Act: -0.1700
Data Index: 2400659 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8228. Min Range: -2.8228
Max Act: 2.7591. Min Act: -0.1700
Data Index: 3294564 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8228. Min Range: -2.8228
Max Act: 2.7272. Min Act: -0.1700
Data Index: 6066220 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8228. Min Range: -2.8228
Max Act: 2.6952. Min Act: -0.1700
Data Index: 2541212 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8228. Min Range: -2.8228
Max Act: 2.7432. Min Act: -0.1700
Data Index: 6883456 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8228. Min Range: -2.8228
Max Act: 2.6631. Min Act: -0.1700
Data Index: 1666902 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8228. Min Range: -2.8228
Max Act: 2.6952. Min Act: -0.1700
Data Index: 8705168 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8228. Min Range: -2.8228
Max Act: 2.6631. Min Act: -0.1700
Data Index: 7716584 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8228. Min Range: -2.8228
Max Act: 2.6792. Min Act: -0.1700
Data Index: 6008833 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8228. Min Range: -2.8228
Max Act: 2.6952. Min Act: -0.1700
Data Index: 2541213 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8228. Min Range: -2.8228
Max Act: 2.6952. Min Act: -0.1700
Data Index: 693348 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8228. Min Range: -2.8228
Max Act: 2.6631. Min Act: -0.1700
Data Index: 6645556 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8228. Min Range: -2.8228
Max Act: 2.6150. Min Act: -0.1700
Data Index: 3040962 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8228. Min Range: -2.8228
Max Act: 2.6792. Min Act: -0.1700
Data Index: 1480260 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8228. Min Range: -2.8228
Max Act: 2.6792. Min Act: -0.1700
Data Index: 6548879 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8228. Min Range: -2.8228
Max Act: 2.6631. Min Act: -0.1700
Data Index: 1319239 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19