Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3808 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4792. Min Range: -2.4792
Max Act: 2.4792. Min Act: -0.1700
Data Index: 5905000 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4792. Min Range: -2.4792
Max Act: 2.4630. Min Act: -0.1700
Data Index: 8599618 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4792. Min Range: -2.4792
Max Act: 2.4468. Min Act: -0.1700
Data Index: 6522485 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4792. Min Range: -2.4792
Max Act: 2.4468. Min Act: -0.1700
Data Index: 5131533 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4792. Min Range: -2.4792
Max Act: 2.4630. Min Act: -0.1700
Data Index: 4400769 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4792. Min Range: -2.4792
Max Act: 2.4468. Min Act: -0.1700
Data Index: 4961590 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4792. Min Range: -2.4792
Max Act: 2.4468. Min Act: -0.1700
Data Index: 269712 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4792. Min Range: -2.4792
Max Act: 2.4468. Min Act: -0.1700
Data Index: 5946725 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4792. Min Range: -2.4792
Max Act: 2.4468. Min Act: -0.1700
Data Index: 6522486 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4792. Min Range: -2.4792
Max Act: 2.4305. Min Act: -0.1700
Data Index: 3973044 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4792. Min Range: -2.4792
Max Act: 2.4142. Min Act: -0.1700
Data Index: 508457 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4792. Min Range: -2.4792
Max Act: 2.4142. Min Act: -0.1700
Data Index: 8213729 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4792. Min Range: -2.4792
Max Act: 2.4305. Min Act: -0.1700
Data Index: 4961589 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4792. Min Range: -2.4792
Max Act: 2.3979. Min Act: -0.1700
Data Index: 7641246 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4792. Min Range: -2.4792
Max Act: 2.4142. Min Act: -0.1700
Data Index: 3462248 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4792. Min Range: -2.4792
Max Act: 2.3815. Min Act: -0.1700
Data Index: 5158850 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4792. Min Range: -2.4792
Max Act: 2.3815. Min Act: -0.1700
Data Index: 7358971 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4792. Min Range: -2.4792
Max Act: 2.3979. Min Act: -0.1700
Data Index: 1706358 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4792. Min Range: -2.4792
Max Act: 2.3488. Min Act: -0.1700
Data Index: 1099545 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4792. Min Range: -2.4792
Max Act: 2.3815. Min Act: -0.1700
Data Index: 4461310 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19