Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5808 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8397. Min Range: -7.8397
Max Act: 7.8397. Min Act: -0.1700
Data Index: 191270 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8397. Min Range: -7.8397
Max Act: 7.7147. Min Act: -0.1700
Data Index: 1048293 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8397. Min Range: -7.8397
Max Act: 7.3397. Min Act: -0.1700
Data Index: 7153072 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8397. Min Range: -7.8397
Max Act: 7.1834. Min Act: -0.1700
Data Index: 1636106 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8397. Min Range: -7.8397
Max Act: 7.1522. Min Act: -0.1700
Data Index: 7801838 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8397. Min Range: -7.8397
Max Act: 7.1209. Min Act: -0.1700
Data Index: 8407105 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8397. Min Range: -7.8397
Max Act: 7.0584. Min Act: -0.1700
Data Index: 6507218 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8397. Min Range: -7.8397
Max Act: 7.0584. Min Act: -0.1700
Data Index: 8413094 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8397. Min Range: -7.8397
Max Act: 7.0272. Min Act: -0.1700
Data Index: 4636976 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8397. Min Range: -7.8397
Max Act: 6.9022. Min Act: -0.1700
Data Index: 6377747 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8397. Min Range: -7.8397
Max Act: 6.8709. Min Act: -0.1700
Data Index: 6893767 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8397. Min Range: -7.8397
Max Act: 6.8397. Min Act: -0.1700
Data Index: 7125438 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8397. Min Range: -7.8397
Max Act: 6.8709. Min Act: -0.1700
Data Index: 8229188 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8397. Min Range: -7.8397
Max Act: 6.7772. Min Act: -0.1700
Data Index: 4840577 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8397. Min Range: -7.8397
Max Act: 6.8084. Min Act: -0.1700
Data Index: 6501869 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8397. Min Range: -7.8397
Max Act: 6.7459. Min Act: -0.1700
Data Index: 118102 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8397. Min Range: -7.8397
Max Act: 6.7459. Min Act: -0.1700
Data Index: 1366018 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8397. Min Range: -7.8397
Max Act: 6.7147. Min Act: -0.1700
Data Index: 3693442 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8397. Min Range: -7.8397
Max Act: 6.7147. Min Act: -0.1700
Data Index: 7900289 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8397. Min Range: -7.8397
Max Act: 6.7147. Min Act: -0.1700
Data Index: 874988 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19