Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3485 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.6960. Min Act: -0.1700
Data Index: 8365038 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.6023. Min Act: -0.1700
Data Index: 2130280 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.4148. Min Act: -0.1700
Data Index: 280810 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.3835. Min Act: -0.1700
Data Index: 4652433 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.4460. Min Act: -0.1700
Data Index: 1317101 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.3835. Min Act: -0.1700
Data Index: 6441313 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.3835. Min Act: -0.1700
Data Index: 4039370 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.3523. Min Act: -0.1700
Data Index: 3004183 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.3523. Min Act: -0.1700
Data Index: 7821836 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.3523. Min Act: -0.1700
Data Index: 799910 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.3210. Min Act: -0.1700
Data Index: 3004185 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.3210. Min Act: -0.1700
Data Index: 1349492 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.2898. Min Act: -0.1700
Data Index: 6462166 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.2898. Min Act: -0.1700
Data Index: 2822438 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.2898. Min Act: -0.1700
Data Index: 6022586 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.2898. Min Act: -0.1700
Data Index: 3305825 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.2585. Min Act: -0.1700
Data Index: 3941469 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.2898. Min Act: -0.1700
Data Index: 2742216 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.2898. Min Act: -0.1700
Data Index: 6332337 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.2585. Min Act: -0.1700
Data Index: 152612 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19