Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2979 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9664. Min Range: -2.9664
Max Act: 2.9664. Min Act: -0.1700
Data Index: 3446498 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9664. Min Range: -2.9664
Max Act: 2.9189. Min Act: -0.1700
Data Index: 573999 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9664. Min Range: -2.9664
Max Act: 2.9505. Min Act: -0.1700
Data Index: 2546928 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9664. Min Range: -2.9664
Max Act: 2.9030. Min Act: -0.1700
Data Index: 185594 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9664. Min Range: -2.9664
Max Act: 2.8713. Min Act: -0.1700
Data Index: 5681602 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9664. Min Range: -2.9664
Max Act: 2.8872. Min Act: -0.1700
Data Index: 4985113 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9664. Min Range: -2.9664
Max Act: 2.8713. Min Act: -0.1700
Data Index: 3652538 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9664. Min Range: -2.9664
Max Act: 2.8713. Min Act: -0.1700
Data Index: 7154340 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9664. Min Range: -2.9664
Max Act: 2.8713. Min Act: -0.1700
Data Index: 7198199 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9664. Min Range: -2.9664
Max Act: 2.8713. Min Act: -0.1700
Data Index: 8535810 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9664. Min Range: -2.9664
Max Act: 2.8713. Min Act: -0.1700
Data Index: 6374862 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9664. Min Range: -2.9664
Max Act: 2.8713. Min Act: -0.1700
Data Index: 2479443 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9664. Min Range: -2.9664
Max Act: 2.8077. Min Act: -0.1700
Data Index: 5433003 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9664. Min Range: -2.9664
Max Act: 2.7758. Min Act: -0.1700
Data Index: 2339154 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9664. Min Range: -2.9664
Max Act: 2.7918. Min Act: -0.1700
Data Index: 5720773 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9664. Min Range: -2.9664
Max Act: 2.7918. Min Act: -0.1700
Data Index: 8056974 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9664. Min Range: -2.9664
Max Act: 2.7918. Min Act: -0.1700
Data Index: 849251 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9664. Min Range: -2.9664
Max Act: 2.8395. Min Act: -0.1700
Data Index: 4940702 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9664. Min Range: -2.9664
Max Act: 2.7758. Min Act: -0.1700
Data Index: 6679869 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9664. Min Range: -2.9664
Max Act: 2.7758. Min Act: -0.1700
Data Index: 2587360 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19