Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4856 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9786. Min Range: -9.9786
Max Act: 9.9786. Min Act: -0.1700
Data Index: 6725294 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9786. Min Range: -9.9786
Max Act: 9.9161. Min Act: -0.1700
Data Index: 3566695 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9786. Min Range: -9.9786
Max Act: 9.7911. Min Act: -0.1700
Data Index: 365673 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9786. Min Range: -9.9786
Max Act: 9.6661. Min Act: -0.1700
Data Index: 3494188 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9786. Min Range: -9.9786
Max Act: 9.6036. Min Act: -0.1700
Data Index: 7221907 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9786. Min Range: -9.9786
Max Act: 9.5411. Min Act: -0.1700
Data Index: 1922458 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9786. Min Range: -9.9786
Max Act: 9.5411. Min Act: -0.1700
Data Index: 4710389 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9786. Min Range: -9.9786
Max Act: 9.5411. Min Act: -0.1700
Data Index: 4926211 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9786. Min Range: -9.9786
Max Act: 9.4161. Min Act: -0.1700
Data Index: 7845750 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9786. Min Range: -9.9786
Max Act: 9.4786. Min Act: -0.1700
Data Index: 2315796 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9786. Min Range: -9.9786
Max Act: 9.4161. Min Act: -0.1700
Data Index: 629132 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9786. Min Range: -9.9786
Max Act: 9.4161. Min Act: -0.1700
Data Index: 7667189 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9786. Min Range: -9.9786
Max Act: 9.2911. Min Act: -0.1700
Data Index: 6321170 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9786. Min Range: -9.9786
Max Act: 9.3536. Min Act: -0.1700
Data Index: 6465533 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9786. Min Range: -9.9786
Max Act: 9.3536. Min Act: -0.1700
Data Index: 6882501 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9786. Min Range: -9.9786
Max Act: 9.3536. Min Act: -0.1700
Data Index: 654563 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9786. Min Range: -9.9786
Max Act: 9.2911. Min Act: -0.1700
Data Index: 2212412 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9786. Min Range: -9.9786
Max Act: 9.3536. Min Act: -0.1700
Data Index: 8739908 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9786. Min Range: -9.9786
Max Act: 9.2286. Min Act: -0.1700
Data Index: 7227447 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9786. Min Range: -9.9786
Max Act: 9.2286. Min Act: -0.1700
Data Index: 3841015 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19