Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5849 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.9022. Min Act: -0.1700
Data Index: 3994200 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.8085. Min Act: -0.1700
Data Index: 6173645 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.6522. Min Act: -0.1700
Data Index: 636223 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.5897. Min Act: -0.1700
Data Index: 3357733 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.4647. Min Act: -0.1700
Data Index: 8076382 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.4960. Min Act: -0.1700
Data Index: 6361674 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.4335. Min Act: -0.1700
Data Index: 5855091 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.4335. Min Act: -0.1700
Data Index: 6766460 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.4335. Min Act: -0.1700
Data Index: 1647336 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.4022. Min Act: -0.1700
Data Index: 7106074 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.4022. Min Act: -0.1700
Data Index: 1402302 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.4022. Min Act: -0.1700
Data Index: 3797655 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.3710. Min Act: -0.1700
Data Index: 3613255 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.4022. Min Act: -0.1700
Data Index: 628923 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.4022. Min Act: -0.1700
Data Index: 4658164 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.3710. Min Act: -0.1700
Data Index: 4605212 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.3397. Min Act: -0.1700
Data Index: 7055747 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.3085. Min Act: -0.1700
Data Index: 7098040 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.2772. Min Act: -0.1700
Data Index: 1766718 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.3397. Min Act: -0.1700
Data Index: 3727621 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19