Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2963 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8994. Min Range: -6.8994
Max Act: 6.8994. Min Act: -0.1700
Data Index: 1574795 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8994. Min Range: -6.8994
Max Act: 6.7744. Min Act: -0.1700
Data Index: 2633291 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8994. Min Range: -6.8994
Max Act: 6.7119. Min Act: -0.1700
Data Index: 1068019 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8994. Min Range: -6.8994
Max Act: 6.7431. Min Act: -0.1700
Data Index: 8567665 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8994. Min Range: -6.8994
Max Act: 6.6494. Min Act: -0.1700
Data Index: 4549819 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8994. Min Range: -6.8994
Max Act: 6.5556. Min Act: -0.1700
Data Index: 3127773 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8994. Min Range: -6.8994
Max Act: 6.5556. Min Act: -0.1700
Data Index: 7240450 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8994. Min Range: -6.8994
Max Act: 6.5556. Min Act: -0.1700
Data Index: 2045539 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8994. Min Range: -6.8994
Max Act: 6.5244. Min Act: -0.1700
Data Index: 8055262 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8994. Min Range: -6.8994
Max Act: 6.5244. Min Act: -0.1700
Data Index: 4713414 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8994. Min Range: -6.8994
Max Act: 6.5244. Min Act: -0.1700
Data Index: 3441770 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8994. Min Range: -6.8994
Max Act: 6.4619. Min Act: -0.1700
Data Index: 2714911 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8994. Min Range: -6.8994
Max Act: 6.3994. Min Act: -0.1700
Data Index: 7426679 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8994. Min Range: -6.8994
Max Act: 6.4306. Min Act: -0.1700
Data Index: 3538971 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8994. Min Range: -6.8994
Max Act: 6.3994. Min Act: -0.1700
Data Index: 4240932 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8994. Min Range: -6.8994
Max Act: 6.3994. Min Act: -0.1700
Data Index: 2347909 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8994. Min Range: -6.8994
Max Act: 6.3994. Min Act: -0.1700
Data Index: 1658226 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8994. Min Range: -6.8994
Max Act: 6.3681. Min Act: -0.1700
Data Index: 4425381 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8994. Min Range: -6.8994
Max Act: 6.3369. Min Act: -0.1700
Data Index: 1582487 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8994. Min Range: -6.8994
Max Act: 6.3369. Min Act: -0.1700
Data Index: 5038669 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19