Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2641 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6854. Min Range: -7.6854
Max Act: 7.6854. Min Act: -0.1700
Data Index: 707786 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6854. Min Range: -7.6854
Max Act: 7.3104. Min Act: -0.1700
Data Index: 977280 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6854. Min Range: -7.6854
Max Act: 7.2479. Min Act: -0.1700
Data Index: 4256844 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6854. Min Range: -7.6854
Max Act: 7.1541. Min Act: -0.1700
Data Index: 145677 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6854. Min Range: -7.6854
Max Act: 7.0604. Min Act: -0.1700
Data Index: 4771419 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6854. Min Range: -7.6854
Max Act: 7.0916. Min Act: -0.1700
Data Index: 4421915 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6854. Min Range: -7.6854
Max Act: 7.0291. Min Act: -0.1700
Data Index: 885987 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6854. Min Range: -7.6854
Max Act: 6.9979. Min Act: -0.1700
Data Index: 1543015 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6854. Min Range: -7.6854
Max Act: 6.9979. Min Act: -0.1700
Data Index: 2905955 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6854. Min Range: -7.6854
Max Act: 6.9666. Min Act: -0.1700
Data Index: 835270 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6854. Min Range: -7.6854
Max Act: 6.9041. Min Act: -0.1700
Data Index: 3554380 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6854. Min Range: -7.6854
Max Act: 6.8729. Min Act: -0.1700
Data Index: 6208058 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6854. Min Range: -7.6854
Max Act: 6.8416. Min Act: -0.1700
Data Index: 4534556 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6854. Min Range: -7.6854
Max Act: 6.8104. Min Act: -0.1700
Data Index: 7507879 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6854. Min Range: -7.6854
Max Act: 6.7791. Min Act: -0.1700
Data Index: 1132801 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6854. Min Range: -7.6854
Max Act: 6.7791. Min Act: -0.1700
Data Index: 2255461 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6854. Min Range: -7.6854
Max Act: 6.7791. Min Act: -0.1700
Data Index: 7820685 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6854. Min Range: -7.6854
Max Act: 6.7791. Min Act: -0.1700
Data Index: 3309053 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6854. Min Range: -7.6854
Max Act: 6.7479. Min Act: -0.1700
Data Index: 4882990 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6854. Min Range: -7.6854
Max Act: 6.7166. Min Act: -0.1700
Data Index: 394478 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19