Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1990 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7650. Min Range: -5.7650
Max Act: 5.7650. Min Act: -0.1700
Data Index: 3659903 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7650. Min Range: -5.7650
Max Act: 5.6088. Min Act: -0.1700
Data Index: 8674706 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7650. Min Range: -5.7650
Max Act: 5.4838. Min Act: -0.1700
Data Index: 1345892 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7650. Min Range: -5.7650
Max Act: 5.4838. Min Act: -0.1700
Data Index: 5104185 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7650. Min Range: -5.7650
Max Act: 5.4213. Min Act: -0.1700
Data Index: 1125866 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7650. Min Range: -5.7650
Max Act: 5.3900. Min Act: -0.1700
Data Index: 8525703 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7650. Min Range: -5.7650
Max Act: 5.3900. Min Act: -0.1700
Data Index: 4938004 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7650. Min Range: -5.7650
Max Act: 5.3588. Min Act: -0.1700
Data Index: 661594 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7650. Min Range: -5.7650
Max Act: 5.3275. Min Act: -0.1700
Data Index: 6920450 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7650. Min Range: -5.7650
Max Act: 5.2963. Min Act: -0.1700
Data Index: 3237038 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7650. Min Range: -5.7650
Max Act: 5.3275. Min Act: -0.1700
Data Index: 6695540 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7650. Min Range: -5.7650
Max Act: 5.2650. Min Act: -0.1700
Data Index: 8414382 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7650. Min Range: -5.7650
Max Act: 5.2650. Min Act: -0.1700
Data Index: 5318280 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7650. Min Range: -5.7650
Max Act: 5.2963. Min Act: -0.1700
Data Index: 8829536 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7650. Min Range: -5.7650
Max Act: 5.2338. Min Act: -0.1700
Data Index: 6117189 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7650. Min Range: -5.7650
Max Act: 5.2025. Min Act: -0.1700
Data Index: 7721610 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7650. Min Range: -5.7650
Max Act: 5.2650. Min Act: -0.1700
Data Index: 5783499 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7650. Min Range: -5.7650
Max Act: 5.2338. Min Act: -0.1700
Data Index: 1083495 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7650. Min Range: -5.7650
Max Act: 5.2338. Min Act: -0.1700
Data Index: 887051 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7650. Min Range: -5.7650
Max Act: 5.1713. Min Act: -0.1700
Data Index: 2435309 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19