Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3448 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5727. Min Range: -6.5727
Max Act: 6.5727. Min Act: -0.1700
Data Index: 4713156 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5727. Min Range: -6.5727
Max Act: 6.5415. Min Act: -0.1700
Data Index: 93314 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5727. Min Range: -6.5727
Max Act: 6.3852. Min Act: -0.1700
Data Index: 2380575 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5727. Min Range: -6.5727
Max Act: 6.3540. Min Act: -0.1700
Data Index: 1176719 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5727. Min Range: -6.5727
Max Act: 6.4165. Min Act: -0.1700
Data Index: 7640268 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5727. Min Range: -6.5727
Max Act: 6.3540. Min Act: -0.1700
Data Index: 7476614 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5727. Min Range: -6.5727
Max Act: 6.3852. Min Act: -0.1700
Data Index: 7110178 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5727. Min Range: -6.5727
Max Act: 6.3540. Min Act: -0.1700
Data Index: 1259308 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5727. Min Range: -6.5727
Max Act: 6.2915. Min Act: -0.1700
Data Index: 3229135 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5727. Min Range: -6.5727
Max Act: 6.2915. Min Act: -0.1700
Data Index: 650925 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5727. Min Range: -6.5727
Max Act: 6.2915. Min Act: -0.1700
Data Index: 5715200 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5727. Min Range: -6.5727
Max Act: 6.2602. Min Act: -0.1700
Data Index: 338756 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5727. Min Range: -6.5727
Max Act: 6.2602. Min Act: -0.1700
Data Index: 2201666 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5727. Min Range: -6.5727
Max Act: 6.2602. Min Act: -0.1700
Data Index: 7123150 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5727. Min Range: -6.5727
Max Act: 6.2290. Min Act: -0.1700
Data Index: 6753387 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5727. Min Range: -6.5727
Max Act: 6.1977. Min Act: -0.1700
Data Index: 7374803 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5727. Min Range: -6.5727
Max Act: 6.1977. Min Act: -0.1700
Data Index: 1585224 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5727. Min Range: -6.5727
Max Act: 6.1665. Min Act: -0.1700
Data Index: 3697767 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5727. Min Range: -6.5727
Max Act: 6.1977. Min Act: -0.1700
Data Index: 6665581 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5727. Min Range: -6.5727
Max Act: 6.1665. Min Act: -0.1700
Data Index: 5179400 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19