Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6025 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4233. Min Range: -7.4233
Max Act: 7.4233. Min Act: -0.1700
Data Index: 2049637 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4233. Min Range: -7.4233
Max Act: 7.2983. Min Act: -0.1700
Data Index: 7128796 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4233. Min Range: -7.4233
Max Act: 7.2671. Min Act: -0.1700
Data Index: 5545028 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4233. Min Range: -7.4233
Max Act: 7.2358. Min Act: -0.1700
Data Index: 6342356 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4233. Min Range: -7.4233
Max Act: 7.0796. Min Act: -0.1700
Data Index: 4166646 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4233. Min Range: -7.4233
Max Act: 7.0483. Min Act: -0.1700
Data Index: 5399999 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4233. Min Range: -7.4233
Max Act: 7.0171. Min Act: -0.1700
Data Index: 2968818 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4233. Min Range: -7.4233
Max Act: 6.9546. Min Act: -0.1700
Data Index: 8067696 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4233. Min Range: -7.4233
Max Act: 6.9233. Min Act: -0.1700
Data Index: 1591016 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4233. Min Range: -7.4233
Max Act: 6.8608. Min Act: -0.1700
Data Index: 2690691 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4233. Min Range: -7.4233
Max Act: 6.8608. Min Act: -0.1700
Data Index: 2037149 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4233. Min Range: -7.4233
Max Act: 6.8296. Min Act: -0.1700
Data Index: 5707834 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4233. Min Range: -7.4233
Max Act: 6.7983. Min Act: -0.1700
Data Index: 4061289 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4233. Min Range: -7.4233
Max Act: 6.7983. Min Act: -0.1700
Data Index: 58366 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4233. Min Range: -7.4233
Max Act: 6.7358. Min Act: -0.1700
Data Index: 1486030 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4233. Min Range: -7.4233
Max Act: 6.7046. Min Act: -0.1700
Data Index: 2582044 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4233. Min Range: -7.4233
Max Act: 6.6733. Min Act: -0.1700
Data Index: 6781876 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4233. Min Range: -7.4233
Max Act: 6.6421. Min Act: -0.1700
Data Index: 1180947 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4233. Min Range: -7.4233
Max Act: 6.6421. Min Act: -0.1700
Data Index: 4394366 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4233. Min Range: -7.4233
Max Act: 6.6421. Min Act: -0.1700
Data Index: 1323973 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19