Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3532 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4066. Min Range: -8.4066
Max Act: 8.4066. Min Act: -0.1700
Data Index: 5591546 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4066. Min Range: -8.4066
Max Act: 8.2191. Min Act: -0.1700
Data Index: 6658900 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4066. Min Range: -8.4066
Max Act: 8.1566. Min Act: -0.1700
Data Index: 4515700 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4066. Min Range: -8.4066
Max Act: 8.0941. Min Act: -0.1700
Data Index: 1507690 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4066. Min Range: -8.4066
Max Act: 7.9691. Min Act: -0.1700
Data Index: 1503068 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4066. Min Range: -8.4066
Max Act: 7.9066. Min Act: -0.1700
Data Index: 8367274 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4066. Min Range: -8.4066
Max Act: 7.8441. Min Act: -0.1700
Data Index: 8589660 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4066. Min Range: -8.4066
Max Act: 7.8128. Min Act: -0.1700
Data Index: 5470497 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4066. Min Range: -8.4066
Max Act: 7.7816. Min Act: -0.1700
Data Index: 8676442 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4066. Min Range: -8.4066
Max Act: 7.7191. Min Act: -0.1700
Data Index: 2591590 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4066. Min Range: -8.4066
Max Act: 7.6878. Min Act: -0.1700
Data Index: 6706674 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4066. Min Range: -8.4066
Max Act: 7.6878. Min Act: -0.1700
Data Index: 6826880 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4066. Min Range: -8.4066
Max Act: 7.7191. Min Act: -0.1700
Data Index: 7965037 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4066. Min Range: -8.4066
Max Act: 7.6566. Min Act: -0.1700
Data Index: 2301946 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4066. Min Range: -8.4066
Max Act: 7.6566. Min Act: -0.1700
Data Index: 7753979 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4066. Min Range: -8.4066
Max Act: 7.6253. Min Act: -0.1700
Data Index: 2336673 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4066. Min Range: -8.4066
Max Act: 7.5941. Min Act: -0.1700
Data Index: 8121318 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4066. Min Range: -8.4066
Max Act: 7.5941. Min Act: -0.1700
Data Index: 471009 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4066. Min Range: -8.4066
Max Act: 7.6253. Min Act: -0.1700
Data Index: 219576 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4066. Min Range: -8.4066
Max Act: 7.5941. Min Act: -0.1700
Data Index: 4972065 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19