Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4486 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6813. Min Range: -5.6813
Max Act: 5.6813. Min Act: -0.1700
Data Index: 8156087 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6813. Min Range: -5.6813
Max Act: 5.3063. Min Act: -0.1700
Data Index: 7212812 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6813. Min Range: -5.6813
Max Act: 5.2750. Min Act: -0.1700
Data Index: 2328631 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6813. Min Range: -5.6813
Max Act: 5.2125. Min Act: -0.1700
Data Index: 1451422 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6813. Min Range: -5.6813
Max Act: 5.1813. Min Act: -0.1700
Data Index: 417031 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6813. Min Range: -5.6813
Max Act: 5.2125. Min Act: -0.1700
Data Index: 6998370 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6813. Min Range: -5.6813
Max Act: 5.1813. Min Act: -0.1700
Data Index: 8185299 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6813. Min Range: -5.6813
Max Act: 5.1500. Min Act: -0.1700
Data Index: 5039710 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6813. Min Range: -5.6813
Max Act: 5.1500. Min Act: -0.1700
Data Index: 1596168 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6813. Min Range: -5.6813
Max Act: 5.1188. Min Act: -0.1700
Data Index: 7557779 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6813. Min Range: -5.6813
Max Act: 5.1500. Min Act: -0.1700
Data Index: 5913210 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6813. Min Range: -5.6813
Max Act: 5.1500. Min Act: -0.1700
Data Index: 4317743 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6813. Min Range: -5.6813
Max Act: 5.1188. Min Act: -0.1700
Data Index: 1741582 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6813. Min Range: -5.6813
Max Act: 5.0875. Min Act: -0.1700
Data Index: 1498898 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6813. Min Range: -5.6813
Max Act: 5.0875. Min Act: -0.1700
Data Index: 6015419 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6813. Min Range: -5.6813
Max Act: 5.0563. Min Act: -0.1700
Data Index: 5776310 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6813. Min Range: -5.6813
Max Act: 5.0250. Min Act: -0.1700
Data Index: 2207445 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6813. Min Range: -5.6813
Max Act: 5.0250. Min Act: -0.1700
Data Index: 8801278 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6813. Min Range: -5.6813
Max Act: 4.9938. Min Act: -0.1700
Data Index: 997139 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6813. Min Range: -5.6813
Max Act: 5.0250. Min Act: -0.1700
Data Index: 3251902 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19