Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4681 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2627. Min Range: -5.2627
Max Act: 5.2627. Min Act: -0.1700
Data Index: 2219383 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2627. Min Range: -5.2627
Max Act: 5.2314. Min Act: -0.1700
Data Index: 1664349 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2627. Min Range: -5.2627
Max Act: 5.2314. Min Act: -0.1700
Data Index: 3174852 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2627. Min Range: -5.2627
Max Act: 5.2002. Min Act: -0.1700
Data Index: 2233511 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2627. Min Range: -5.2627
Max Act: 5.1689. Min Act: -0.1700
Data Index: 4915515 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2627. Min Range: -5.2627
Max Act: 5.2002. Min Act: -0.1700
Data Index: 5065212 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2627. Min Range: -5.2627
Max Act: 5.2002. Min Act: -0.1700
Data Index: 2883248 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2627. Min Range: -5.2627
Max Act: 5.1064. Min Act: -0.1700
Data Index: 1962836 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2627. Min Range: -5.2627
Max Act: 5.1064. Min Act: -0.1700
Data Index: 7648569 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2627. Min Range: -5.2627
Max Act: 5.1064. Min Act: -0.1700
Data Index: 6993101 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2627. Min Range: -5.2627
Max Act: 5.0752. Min Act: -0.1700
Data Index: 3127725 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2627. Min Range: -5.2627
Max Act: 5.0752. Min Act: -0.1700
Data Index: 4124003 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2627. Min Range: -5.2627
Max Act: 5.1064. Min Act: -0.1700
Data Index: 1226296 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2627. Min Range: -5.2627
Max Act: 5.0752. Min Act: -0.1700
Data Index: 8514184 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2627. Min Range: -5.2627
Max Act: 5.0439. Min Act: -0.1700
Data Index: 6536398 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2627. Min Range: -5.2627
Max Act: 4.9814. Min Act: -0.1700
Data Index: 4655988 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2627. Min Range: -5.2627
Max Act: 5.0439. Min Act: -0.1700
Data Index: 8327733 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2627. Min Range: -5.2627
Max Act: 5.0127. Min Act: -0.1700
Data Index: 134052 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2627. Min Range: -5.2627
Max Act: 4.9814. Min Act: -0.1700
Data Index: 3170938 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2627. Min Range: -5.2627
Max Act: 4.9814. Min Act: -0.1700
Data Index: 2781312 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19