Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6395 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7157. Min Range: -6.7157
Max Act: 6.7157. Min Act: -0.1700
Data Index: 3161357 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7157. Min Range: -6.7157
Max Act: 5.9344. Min Act: -0.1700
Data Index: 1174670 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7157. Min Range: -6.7157
Max Act: 5.9032. Min Act: -0.1700
Data Index: 1957778 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7157. Min Range: -6.7157
Max Act: 5.9344. Min Act: -0.1700
Data Index: 3038042 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7157. Min Range: -6.7157
Max Act: 5.9344. Min Act: -0.1700
Data Index: 6250309 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7157. Min Range: -6.7157
Max Act: 5.9032. Min Act: -0.1700
Data Index: 7597806 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7157. Min Range: -6.7157
Max Act: 5.9032. Min Act: -0.1700
Data Index: 6618605 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7157. Min Range: -6.7157
Max Act: 5.9032. Min Act: -0.1700
Data Index: 481427 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7157. Min Range: -6.7157
Max Act: 5.8407. Min Act: -0.1700
Data Index: 8384214 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7157. Min Range: -6.7157
Max Act: 5.8719. Min Act: -0.1700
Data Index: 8154892 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7157. Min Range: -6.7157
Max Act: 5.8094. Min Act: -0.1700
Data Index: 2365995 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7157. Min Range: -6.7157
Max Act: 5.8094. Min Act: -0.1700
Data Index: 3540212 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7157. Min Range: -6.7157
Max Act: 5.8094. Min Act: -0.1700
Data Index: 5661731 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7157. Min Range: -6.7157
Max Act: 5.8094. Min Act: -0.1700
Data Index: 493820 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7157. Min Range: -6.7157
Max Act: 5.7782. Min Act: -0.1700
Data Index: 5191097 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7157. Min Range: -6.7157
Max Act: 5.7469. Min Act: -0.1700
Data Index: 5760514 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7157. Min Range: -6.7157
Max Act: 5.7157. Min Act: -0.1700
Data Index: 414163 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7157. Min Range: -6.7157
Max Act: 5.7157. Min Act: -0.1700
Data Index: 3165882 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7157. Min Range: -6.7157
Max Act: 5.7157. Min Act: -0.1700
Data Index: 2440048 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7157. Min Range: -6.7157
Max Act: 5.6844. Min Act: -0.1700
Data Index: 4489287 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19