Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2405 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6837. Min Range: -3.6837
Max Act: 3.6837. Min Act: -0.1700
Data Index: 94887 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6837. Min Range: -3.6837
Max Act: 3.6054. Min Act: -0.1700
Data Index: 3131142 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6837. Min Range: -3.6837
Max Act: 3.5428. Min Act: -0.1700
Data Index: 5297803 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6837. Min Range: -3.6837
Max Act: 3.5585. Min Act: -0.1700
Data Index: 4243096 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6837. Min Range: -3.6837
Max Act: 3.5272. Min Act: -0.1700
Data Index: 3844317 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6837. Min Range: -3.6837
Max Act: 3.5428. Min Act: -0.1700
Data Index: 1956380 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6837. Min Range: -3.6837
Max Act: 3.5115. Min Act: -0.1700
Data Index: 4457493 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6837. Min Range: -3.6837
Max Act: 3.4802. Min Act: -0.1700
Data Index: 3536562 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6837. Min Range: -3.6837
Max Act: 3.4645. Min Act: -0.1700
Data Index: 6191474 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6837. Min Range: -3.6837
Max Act: 3.4332. Min Act: -0.1700
Data Index: 6470954 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6837. Min Range: -3.6837
Max Act: 3.4488. Min Act: -0.1700
Data Index: 4483838 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6837. Min Range: -3.6837
Max Act: 3.4488. Min Act: -0.1700
Data Index: 8096053 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6837. Min Range: -3.6837
Max Act: 3.4645. Min Act: -0.1700
Data Index: 5031587 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6837. Min Range: -3.6837
Max Act: 3.4175. Min Act: -0.1700
Data Index: 6509278 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6837. Min Range: -3.6837
Max Act: 3.4332. Min Act: -0.1700
Data Index: 264069 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6837. Min Range: -3.6837
Max Act: 3.4332. Min Act: -0.1700
Data Index: 5115592 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6837. Min Range: -3.6837
Max Act: 3.4332. Min Act: -0.1700
Data Index: 8532232 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6837. Min Range: -3.6837
Max Act: 3.4018. Min Act: -0.1700
Data Index: 388000 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6837. Min Range: -3.6837
Max Act: 3.4175. Min Act: -0.1700
Data Index: 7733527 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6837. Min Range: -3.6837
Max Act: 3.4175. Min Act: -0.1700
Data Index: 4132575 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19