Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3049 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6041. Min Range: -6.6041
Max Act: 6.6041. Min Act: -0.1700
Data Index: 6358353 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6041. Min Range: -6.6041
Max Act: 6.5416. Min Act: -0.1700
Data Index: 3339728 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6041. Min Range: -6.6041
Max Act: 6.4791. Min Act: -0.1700
Data Index: 6276674 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6041. Min Range: -6.6041
Max Act: 6.4479. Min Act: -0.1700
Data Index: 6276675 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6041. Min Range: -6.6041
Max Act: 6.4166. Min Act: -0.1700
Data Index: 2063092 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6041. Min Range: -6.6041
Max Act: 6.4166. Min Act: -0.1700
Data Index: 6276677 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6041. Min Range: -6.6041
Max Act: 6.4166. Min Act: -0.1700
Data Index: 8038487 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6041. Min Range: -6.6041
Max Act: 6.3854. Min Act: -0.1700
Data Index: 5069087 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6041. Min Range: -6.6041
Max Act: 6.2604. Min Act: -0.1700
Data Index: 8799873 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6041. Min Range: -6.6041
Max Act: 6.2291. Min Act: -0.1700
Data Index: 1347575 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6041. Min Range: -6.6041
Max Act: 6.1666. Min Act: -0.1700
Data Index: 3339724 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6041. Min Range: -6.6041
Max Act: 6.1354. Min Act: -0.1700
Data Index: 4410331 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6041. Min Range: -6.6041
Max Act: 6.1666. Min Act: -0.1700
Data Index: 3339726 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6041. Min Range: -6.6041
Max Act: 6.1666. Min Act: -0.1700
Data Index: 7812377 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6041. Min Range: -6.6041
Max Act: 6.0416. Min Act: -0.1700
Data Index: 506497 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6041. Min Range: -6.6041
Max Act: 6.0416. Min Act: -0.1700
Data Index: 6674039 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6041. Min Range: -6.6041
Max Act: 6.0104. Min Act: -0.1700
Data Index: 2381486 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6041. Min Range: -6.6041
Max Act: 6.0104. Min Act: -0.1700
Data Index: 5292675 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6041. Min Range: -6.6041
Max Act: 6.0104. Min Act: -0.1700
Data Index: 1169355 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6041. Min Range: -6.6041
Max Act: 6.0104. Min Act: -0.1700
Data Index: 7890960 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19