Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 257 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8118. Min Range: -8.8118
Max Act: 8.8118. Min Act: -0.1700
Data Index: 4247622 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8118. Min Range: -8.8118
Max Act: 8.6243. Min Act: -0.1700
Data Index: 2030575 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8118. Min Range: -8.8118
Max Act: 8.6243. Min Act: -0.1700
Data Index: 209982 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8118. Min Range: -8.8118
Max Act: 8.4993. Min Act: -0.1700
Data Index: 2709161 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8118. Min Range: -8.8118
Max Act: 8.4368. Min Act: -0.1700
Data Index: 2063147 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8118. Min Range: -8.8118
Max Act: 8.4368. Min Act: -0.1700
Data Index: 6177989 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8118. Min Range: -8.8118
Max Act: 8.3743. Min Act: -0.1700
Data Index: 7421221 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8118. Min Range: -8.8118
Max Act: 8.3743. Min Act: -0.1700
Data Index: 493277 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8118. Min Range: -8.8118
Max Act: 8.3118. Min Act: -0.1700
Data Index: 8157615 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8118. Min Range: -8.8118
Max Act: 8.3743. Min Act: -0.1700
Data Index: 3854195 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8118. Min Range: -8.8118
Max Act: 8.3118. Min Act: -0.1700
Data Index: 7562656 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8118. Min Range: -8.8118
Max Act: 8.3743. Min Act: -0.1700
Data Index: 4507846 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8118. Min Range: -8.8118
Max Act: 8.3118. Min Act: -0.1700
Data Index: 6122226 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8118. Min Range: -8.8118
Max Act: 8.3118. Min Act: -0.1700
Data Index: 470537 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8118. Min Range: -8.8118
Max Act: 8.2493. Min Act: -0.1700
Data Index: 5544457 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8118. Min Range: -8.8118
Max Act: 8.2493. Min Act: -0.1700
Data Index: 6611296 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8118. Min Range: -8.8118
Max Act: 8.2493. Min Act: -0.1700
Data Index: 8546277 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8118. Min Range: -8.8118
Max Act: 8.2493. Min Act: -0.1700
Data Index: 2009566 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8118. Min Range: -8.8118
Max Act: 8.2493. Min Act: -0.1700
Data Index: 6756456 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8118. Min Range: -8.8118
Max Act: 8.2493. Min Act: -0.1700
Data Index: 4502463 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19