Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 10 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9169. Min Range: -4.9169
Max Act: 4.9169. Min Act: -0.1700
Data Index: 307204 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9169. Min Range: -4.9169
Max Act: 4.8231. Min Act: -0.1700
Data Index: 4977963 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9169. Min Range: -4.9169
Max Act: 4.8231. Min Act: -0.1700
Data Index: 3981172 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9169. Min Range: -4.9169
Max Act: 4.7606. Min Act: -0.1700
Data Index: 7106362 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9169. Min Range: -4.9169
Max Act: 4.6981. Min Act: -0.1700
Data Index: 2753783 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9169. Min Range: -4.9169
Max Act: 4.7294. Min Act: -0.1700
Data Index: 6348201 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9169. Min Range: -4.9169
Max Act: 4.6981. Min Act: -0.1700
Data Index: 8666014 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9169. Min Range: -4.9169
Max Act: 4.6669. Min Act: -0.1700
Data Index: 4630910 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9169. Min Range: -4.9169
Max Act: 4.6669. Min Act: -0.1700
Data Index: 431752 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9169. Min Range: -4.9169
Max Act: 4.6981. Min Act: -0.1700
Data Index: 8111761 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9169. Min Range: -4.9169
Max Act: 4.6669. Min Act: -0.1700
Data Index: 2402196 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9169. Min Range: -4.9169
Max Act: 4.6669. Min Act: -0.1700
Data Index: 6395553 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9169. Min Range: -4.9169
Max Act: 4.6356. Min Act: -0.1700
Data Index: 4034171 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9169. Min Range: -4.9169
Max Act: 4.6356. Min Act: -0.1700
Data Index: 5435534 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9169. Min Range: -4.9169
Max Act: 4.6044. Min Act: -0.1700
Data Index: 6195379 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9169. Min Range: -4.9169
Max Act: 4.6044. Min Act: -0.1700
Data Index: 255221 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9169. Min Range: -4.9169
Max Act: 4.6044. Min Act: -0.1700
Data Index: 354765 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9169. Min Range: -4.9169
Max Act: 4.5731. Min Act: -0.1700
Data Index: 835473 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9169. Min Range: -4.9169
Max Act: 4.5731. Min Act: -0.1700
Data Index: 1882682 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9169. Min Range: -4.9169
Max Act: 4.5731. Min Act: -0.1700
Data Index: 6583201 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19