Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4057 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3564. Min Range: -6.3564
Max Act: 6.3564. Min Act: -0.1696
Data Index: 2178134 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3564. Min Range: -6.3564
Max Act: 6.2001. Min Act: -0.1700
Data Index: 1088579 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3564. Min Range: -6.3564
Max Act: 6.1689. Min Act: -0.1697
Data Index: 8522615 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3564. Min Range: -6.3564
Max Act: 6.2001. Min Act: -0.1700
Data Index: 4808802 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3564. Min Range: -6.3564
Max Act: 6.1689. Min Act: -0.1700
Data Index: 8281151 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3564. Min Range: -6.3564
Max Act: 6.1689. Min Act: -0.1699
Data Index: 5328857 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3564. Min Range: -6.3564
Max Act: 6.1689. Min Act: -0.1699
Data Index: 2185951 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3564. Min Range: -6.3564
Max Act: 6.1689. Min Act: -0.1700
Data Index: 592351 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3564. Min Range: -6.3564
Max Act: 6.1689. Min Act: -0.1700
Data Index: 4148631 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3564. Min Range: -6.3564
Max Act: 6.1376. Min Act: -0.1700
Data Index: 5689523 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3564. Min Range: -6.3564
Max Act: 6.1376. Min Act: -0.1700
Data Index: 7269218 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3564. Min Range: -6.3564
Max Act: 6.1376. Min Act: -0.1700
Data Index: 8156809 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3564. Min Range: -6.3564
Max Act: 6.1376. Min Act: -0.1696
Data Index: 4684490 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3564. Min Range: -6.3564
Max Act: 6.1064. Min Act: -0.1700
Data Index: 2178135 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3564. Min Range: -6.3564
Max Act: 6.1064. Min Act: -0.1700
Data Index: 6237469 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3564. Min Range: -6.3564
Max Act: 6.1064. Min Act: -0.1700
Data Index: 3545826 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3564. Min Range: -6.3564
Max Act: 6.1064. Min Act: -0.1700
Data Index: 4808803 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3564. Min Range: -6.3564
Max Act: 6.0439. Min Act: -0.1700
Data Index: 1486107 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3564. Min Range: -6.3564
Max Act: 6.0751. Min Act: -0.1700
Data Index: 564969 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3564. Min Range: -6.3564
Max Act: 6.1064. Min Act: -0.1700
Data Index: 172136 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19