Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5412. Min Range: -7.5412
Max Act: 7.5412. Min Act: -0.1700
Data Index: 375043 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5412. Min Range: -7.5412
Max Act: 7.2287. Min Act: -0.1700
Data Index: 1595913 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5412. Min Range: -7.5412
Max Act: 7.1662. Min Act: -0.1700
Data Index: 7244613 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5412. Min Range: -7.5412
Max Act: 7.1037. Min Act: -0.1700
Data Index: 8419727 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5412. Min Range: -7.5412
Max Act: 7.1037. Min Act: -0.1700
Data Index: 8163961 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5412. Min Range: -7.5412
Max Act: 7.0725. Min Act: -0.1700
Data Index: 1389679 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5412. Min Range: -7.5412
Max Act: 7.0412. Min Act: -0.1700
Data Index: 7349768 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5412. Min Range: -7.5412
Max Act: 7.0412. Min Act: -0.1700
Data Index: 6797657 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5412. Min Range: -7.5412
Max Act: 7.0100. Min Act: -0.1700
Data Index: 2257738 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5412. Min Range: -7.5412
Max Act: 6.9787. Min Act: -0.1700
Data Index: 1299976 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5412. Min Range: -7.5412
Max Act: 6.9787. Min Act: -0.1700
Data Index: 4715338 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5412. Min Range: -7.5412
Max Act: 6.9475. Min Act: -0.1700
Data Index: 3528572 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5412. Min Range: -7.5412
Max Act: 6.9475. Min Act: -0.1700
Data Index: 6888128 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5412. Min Range: -7.5412
Max Act: 6.9475. Min Act: -0.1700
Data Index: 1026140 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5412. Min Range: -7.5412
Max Act: 6.9162. Min Act: -0.1700
Data Index: 2259817 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5412. Min Range: -7.5412
Max Act: 6.9162. Min Act: -0.1700
Data Index: 5346358 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5412. Min Range: -7.5412
Max Act: 6.9162. Min Act: -0.1700
Data Index: 3118057 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5412. Min Range: -7.5412
Max Act: 6.9162. Min Act: -0.1700
Data Index: 2296197 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5412. Min Range: -7.5412
Max Act: 6.8850. Min Act: -0.1700
Data Index: 7915784 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5412. Min Range: -7.5412
Max Act: 6.8537. Min Act: -0.1700
Data Index: 1329530 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19