Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3337 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9529. Min Range: -5.9529
Max Act: 5.9529. Min Act: -0.1700
Data Index: 7658675 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9529. Min Range: -5.9529
Max Act: 5.7341. Min Act: -0.1700
Data Index: 4243874 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9529. Min Range: -5.9529
Max Act: 5.5779. Min Act: -0.1700
Data Index: 5770633 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9529. Min Range: -5.9529
Max Act: 5.5154. Min Act: -0.1700
Data Index: 8260395 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9529. Min Range: -5.9529
Max Act: 5.5154. Min Act: -0.1700
Data Index: 1493646 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9529. Min Range: -5.9529
Max Act: 5.4841. Min Act: -0.1700
Data Index: 2651147 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9529. Min Range: -5.9529
Max Act: 5.4216. Min Act: -0.1700
Data Index: 2697422 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9529. Min Range: -5.9529
Max Act: 5.3904. Min Act: -0.1700
Data Index: 8020338 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9529. Min Range: -5.9529
Max Act: 5.4216. Min Act: -0.1700
Data Index: 3310212 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9529. Min Range: -5.9529
Max Act: 5.4216. Min Act: -0.1700
Data Index: 5213389 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9529. Min Range: -5.9529
Max Act: 5.4216. Min Act: -0.1700
Data Index: 2489462 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9529. Min Range: -5.9529
Max Act: 5.3904. Min Act: -0.1700
Data Index: 1233616 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9529. Min Range: -5.9529
Max Act: 5.3904. Min Act: -0.1700
Data Index: 8746808 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9529. Min Range: -5.9529
Max Act: 5.3904. Min Act: -0.1700
Data Index: 5568552 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9529. Min Range: -5.9529
Max Act: 5.3591. Min Act: -0.1700
Data Index: 3976987 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9529. Min Range: -5.9529
Max Act: 5.3591. Min Act: -0.1700
Data Index: 149755 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9529. Min Range: -5.9529
Max Act: 5.3279. Min Act: -0.1700
Data Index: 1004050 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9529. Min Range: -5.9529
Max Act: 5.3591. Min Act: -0.1700
Data Index: 3672936 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9529. Min Range: -5.9529
Max Act: 5.3904. Min Act: -0.1700
Data Index: 5814785 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9529. Min Range: -5.9529
Max Act: 5.3279. Min Act: -0.1700
Data Index: 4912329 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19