Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 741 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4456. Min Range: -3.4456
Max Act: 3.4142. Min Act: -0.1700
Data Index: 8610290 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4456. Min Range: -3.4456
Max Act: 3.4142. Min Act: -0.1700
Data Index: 2569387 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4456. Min Range: -3.4456
Max Act: 3.4456. Min Act: -0.1700
Data Index: 213620 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4456. Min Range: -3.4456
Max Act: 3.4299. Min Act: -0.1700
Data Index: 7017263 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4456. Min Range: -3.4456
Max Act: 3.3829. Min Act: -0.1700
Data Index: 4178615 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4456. Min Range: -3.4456
Max Act: 3.3829. Min Act: -0.1700
Data Index: 7205937 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4456. Min Range: -3.4456
Max Act: 3.3672. Min Act: -0.1700
Data Index: 80928 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4456. Min Range: -3.4456
Max Act: 3.3515. Min Act: -0.1700
Data Index: 6428845 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4456. Min Range: -3.4456
Max Act: 3.3515. Min Act: -0.1700
Data Index: 3992327 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4456. Min Range: -3.4456
Max Act: 3.3358. Min Act: -0.1700
Data Index: 7060825 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4456. Min Range: -3.4456
Max Act: 3.2887. Min Act: -0.1700
Data Index: 5214730 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4456. Min Range: -3.4456
Max Act: 3.2887. Min Act: -0.1700
Data Index: 8145340 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4456. Min Range: -3.4456
Max Act: 3.2573. Min Act: -0.1700
Data Index: 405917 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4456. Min Range: -3.4456
Max Act: 3.2416. Min Act: -0.1700
Data Index: 7834704 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4456. Min Range: -3.4456
Max Act: 3.2259. Min Act: -0.1700
Data Index: 4474623 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4456. Min Range: -3.4456
Max Act: 3.2102. Min Act: -0.1700
Data Index: 3484678 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4456. Min Range: -3.4456
Max Act: 3.1945. Min Act: -0.1700
Data Index: 58750 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4456. Min Range: -3.4456
Max Act: 3.1945. Min Act: -0.1700
Data Index: 2497257 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4456. Min Range: -3.4456
Max Act: 3.1945. Min Act: -0.1700
Data Index: 4991460 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4456. Min Range: -3.4456
Max Act: 3.1945. Min Act: -0.1700
Data Index: 4219462 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19