Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4908 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3137. Min Range: -7.3137
Max Act: 7.3137. Min Act: -0.1700
Data Index: 1710370 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3137. Min Range: -7.3137
Max Act: 7.3137. Min Act: -0.1700
Data Index: 6170065 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3137. Min Range: -7.3137
Max Act: 7.1262. Min Act: -0.1700
Data Index: 7340002 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3137. Min Range: -7.3137
Max Act: 7.0950. Min Act: -0.1700
Data Index: 6481320 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3137. Min Range: -7.3137
Max Act: 7.0950. Min Act: -0.1700
Data Index: 4492475 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3137. Min Range: -7.3137
Max Act: 7.0325. Min Act: -0.1700
Data Index: 1898799 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3137. Min Range: -7.3137
Max Act: 7.0325. Min Act: -0.1700
Data Index: 1230630 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3137. Min Range: -7.3137
Max Act: 7.0012. Min Act: -0.1700
Data Index: 163099 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3137. Min Range: -7.3137
Max Act: 7.0012. Min Act: -0.1700
Data Index: 2629155 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3137. Min Range: -7.3137
Max Act: 6.9387. Min Act: -0.1700
Data Index: 4219144 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3137. Min Range: -7.3137
Max Act: 6.9075. Min Act: -0.1700
Data Index: 2372487 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3137. Min Range: -7.3137
Max Act: 6.9075. Min Act: -0.1700
Data Index: 2925290 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3137. Min Range: -7.3137
Max Act: 6.9075. Min Act: -0.1700
Data Index: 3709260 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3137. Min Range: -7.3137
Max Act: 6.8450. Min Act: -0.1700
Data Index: 724298 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3137. Min Range: -7.3137
Max Act: 6.8450. Min Act: -0.1700
Data Index: 5351196 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3137. Min Range: -7.3137
Max Act: 6.8450. Min Act: -0.1700
Data Index: 3574731 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3137. Min Range: -7.3137
Max Act: 6.7825. Min Act: -0.1700
Data Index: 2008750 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3137. Min Range: -7.3137
Max Act: 6.8137. Min Act: -0.1700
Data Index: 8562997 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3137. Min Range: -7.3137
Max Act: 6.8137. Min Act: -0.1700
Data Index: 2473008 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3137. Min Range: -7.3137
Max Act: 6.8137. Min Act: -0.1700
Data Index: 780916 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19