Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3847 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0216. Min Range: -10.0216
Max Act: 10.0216. Min Act: -0.1700
Data Index: 1530810 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0216. Min Range: -10.0216
Max Act: 9.9591. Min Act: -0.1700
Data Index: 4747161 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0216. Min Range: -10.0216
Max Act: 10.0216. Min Act: -0.1700
Data Index: 3335757 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0216. Min Range: -10.0216
Max Act: 9.9591. Min Act: -0.1700
Data Index: 4077408 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0216. Min Range: -10.0216
Max Act: 9.9591. Min Act: -0.1700
Data Index: 4812529 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0216. Min Range: -10.0216
Max Act: 9.8341. Min Act: -0.1700
Data Index: 1893833 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0216. Min Range: -10.0216
Max Act: 9.8966. Min Act: -0.1700
Data Index: 3568841 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0216. Min Range: -10.0216
Max Act: 9.8966. Min Act: -0.1700
Data Index: 2148645 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0216. Min Range: -10.0216
Max Act: 9.8341. Min Act: -0.1700
Data Index: 881921 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0216. Min Range: -10.0216
Max Act: 9.7716. Min Act: -0.1700
Data Index: 1129557 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0216. Min Range: -10.0216
Max Act: 9.7716. Min Act: -0.1700
Data Index: 1933187 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0216. Min Range: -10.0216
Max Act: 9.7716. Min Act: -0.1700
Data Index: 8241205 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0216. Min Range: -10.0216
Max Act: 9.7716. Min Act: -0.1700
Data Index: 8330036 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0216. Min Range: -10.0216
Max Act: 9.7716. Min Act: -0.1700
Data Index: 8066663 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0216. Min Range: -10.0216
Max Act: 9.7091. Min Act: -0.1700
Data Index: 865108 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0216. Min Range: -10.0216
Max Act: 9.7091. Min Act: -0.1700
Data Index: 2655952 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0216. Min Range: -10.0216
Max Act: 9.7091. Min Act: -0.1700
Data Index: 2359259 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0216. Min Range: -10.0216
Max Act: 9.6466. Min Act: -0.1700
Data Index: 2735407 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0216. Min Range: -10.0216
Max Act: 9.6466. Min Act: -0.1700
Data Index: 7445551 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0216. Min Range: -10.0216
Max Act: 9.6466. Min Act: -0.1700
Data Index: 320559 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19