Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3093 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7176. Min Range: -8.7176
Max Act: 8.7176. Min Act: -0.1700
Data Index: 4392916 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7176. Min Range: -8.7176
Max Act: 8.5926. Min Act: -0.1700
Data Index: 2160944 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7176. Min Range: -8.7176
Max Act: 8.4676. Min Act: -0.1700
Data Index: 5700698 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7176. Min Range: -8.7176
Max Act: 8.4051. Min Act: -0.1700
Data Index: 118094 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7176. Min Range: -8.7176
Max Act: 8.4051. Min Act: -0.1700
Data Index: 7951172 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7176. Min Range: -8.7176
Max Act: 8.3426. Min Act: -0.1700
Data Index: 1560355 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7176. Min Range: -8.7176
Max Act: 8.3426. Min Act: -0.1700
Data Index: 7951171 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7176. Min Range: -8.7176
Max Act: 8.2801. Min Act: -0.1700
Data Index: 5193659 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7176. Min Range: -8.7176
Max Act: 8.2801. Min Act: -0.1700
Data Index: 7103627 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7176. Min Range: -8.7176
Max Act: 8.2801. Min Act: -0.1700
Data Index: 4392917 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7176. Min Range: -8.7176
Max Act: 8.2176. Min Act: -0.1700
Data Index: 3831708 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7176. Min Range: -8.7176
Max Act: 8.0926. Min Act: -0.1700
Data Index: 2292398 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7176. Min Range: -8.7176
Max Act: 8.0926. Min Act: -0.1700
Data Index: 2971738 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7176. Min Range: -8.7176
Max Act: 8.0301. Min Act: -0.1700
Data Index: 8671369 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7176. Min Range: -8.7176
Max Act: 8.0301. Min Act: -0.1700
Data Index: 6152216 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7176. Min Range: -8.7176
Max Act: 8.0301. Min Act: -0.1699
Data Index: 7341762 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7176. Min Range: -8.7176
Max Act: 8.0301. Min Act: -0.1700
Data Index: 4995594 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7176. Min Range: -8.7176
Max Act: 8.0301. Min Act: -0.1700
Data Index: 2524304 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7176. Min Range: -8.7176
Max Act: 7.9676. Min Act: -0.1700
Data Index: 7103628 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7176. Min Range: -8.7176
Max Act: 7.9676. Min Act: -0.1700
Data Index: 4433793 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19