Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6085 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6333. Min Range: -5.6333
Max Act: 5.6333. Min Act: -0.1700
Data Index: 7206404 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6333. Min Range: -5.6333
Max Act: 5.6333. Min Act: -0.1700
Data Index: 6684458 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6333. Min Range: -5.6333
Max Act: 5.5083. Min Act: -0.1700
Data Index: 5634446 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6333. Min Range: -5.6333
Max Act: 5.5395. Min Act: -0.1700
Data Index: 6233121 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6333. Min Range: -5.6333
Max Act: 5.5083. Min Act: -0.1700
Data Index: 1303590 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6333. Min Range: -5.6333
Max Act: 5.4458. Min Act: -0.1700
Data Index: 7176929 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6333. Min Range: -5.6333
Max Act: 5.4145. Min Act: -0.1700
Data Index: 2904742 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6333. Min Range: -5.6333
Max Act: 5.4145. Min Act: -0.1700
Data Index: 5707120 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6333. Min Range: -5.6333
Max Act: 5.3833. Min Act: -0.1700
Data Index: 3877338 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6333. Min Range: -5.6333
Max Act: 5.3520. Min Act: -0.1700
Data Index: 4084045 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6333. Min Range: -5.6333
Max Act: 5.3520. Min Act: -0.1700
Data Index: 1360116 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6333. Min Range: -5.6333
Max Act: 5.3520. Min Act: -0.1700
Data Index: 306383 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6333. Min Range: -5.6333
Max Act: 5.3208. Min Act: -0.1700
Data Index: 2316601 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6333. Min Range: -5.6333
Max Act: 5.3208. Min Act: -0.1700
Data Index: 4618383 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6333. Min Range: -5.6333
Max Act: 5.3208. Min Act: -0.1700
Data Index: 6420509 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6333. Min Range: -5.6333
Max Act: 5.3208. Min Act: -0.1700
Data Index: 541706 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6333. Min Range: -5.6333
Max Act: 5.2895. Min Act: -0.1700
Data Index: 3435728 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6333. Min Range: -5.6333
Max Act: 5.3208. Min Act: -0.1700
Data Index: 472305 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6333. Min Range: -5.6333
Max Act: 5.2583. Min Act: -0.1700
Data Index: 904884 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6333. Min Range: -5.6333
Max Act: 5.2583. Min Act: -0.1700
Data Index: 7002601 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19