Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5852 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3374. Min Range: -7.3374
Max Act: 7.3374. Min Act: -0.1700
Data Index: 2585868 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3374. Min Range: -7.3374
Max Act: 7.0249. Min Act: -0.1700
Data Index: 3448517 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3374. Min Range: -7.3374
Max Act: 6.9936. Min Act: -0.1700
Data Index: 802990 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3374. Min Range: -7.3374
Max Act: 6.8374. Min Act: -0.1700
Data Index: 712801 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3374. Min Range: -7.3374
Max Act: 6.8061. Min Act: -0.1700
Data Index: 4306136 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3374. Min Range: -7.3374
Max Act: 6.7124. Min Act: -0.1700
Data Index: 1791997 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3374. Min Range: -7.3374
Max Act: 6.7124. Min Act: -0.1700
Data Index: 5414788 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3374. Min Range: -7.3374
Max Act: 6.6186. Min Act: -0.1700
Data Index: 3017335 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3374. Min Range: -7.3374
Max Act: 6.6186. Min Act: -0.1700
Data Index: 1926932 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3374. Min Range: -7.3374
Max Act: 6.5874. Min Act: -0.1700
Data Index: 485436 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3374. Min Range: -7.3374
Max Act: 6.5561. Min Act: -0.1700
Data Index: 3618755 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3374. Min Range: -7.3374
Max Act: 6.5561. Min Act: -0.1700
Data Index: 6872724 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3374. Min Range: -7.3374
Max Act: 6.5249. Min Act: -0.1700
Data Index: 4522265 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3374. Min Range: -7.3374
Max Act: 6.4936. Min Act: -0.1700
Data Index: 2059912 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3374. Min Range: -7.3374
Max Act: 6.4624. Min Act: -0.1700
Data Index: 771389 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3374. Min Range: -7.3374
Max Act: 6.4936. Min Act: -0.1700
Data Index: 8292445 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3374. Min Range: -7.3374
Max Act: 6.4311. Min Act: -0.1700
Data Index: 7623192 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3374. Min Range: -7.3374
Max Act: 6.4624. Min Act: -0.1700
Data Index: 5273107 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3374. Min Range: -7.3374
Max Act: 6.4936. Min Act: -0.1700
Data Index: 6313271 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3374. Min Range: -7.3374
Max Act: 6.4624. Min Act: -0.1700
Data Index: 644202 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19