Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3942 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0572. Min Range: -5.0572
Max Act: 5.0572. Min Act: -0.1700
Data Index: 227952 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0572. Min Range: -5.0572
Max Act: 4.8697. Min Act: -0.1700
Data Index: 6783426 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0572. Min Range: -5.0572
Max Act: 4.8072. Min Act: -0.1700
Data Index: 7753859 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0572. Min Range: -5.0572
Max Act: 4.7759. Min Act: -0.1700
Data Index: 775863 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0572. Min Range: -5.0572
Max Act: 4.7447. Min Act: -0.1700
Data Index: 1687999 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0572. Min Range: -5.0572
Max Act: 4.6822. Min Act: -0.1700
Data Index: 3403959 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0572. Min Range: -5.0572
Max Act: 4.6197. Min Act: -0.1700
Data Index: 482730 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0572. Min Range: -5.0572
Max Act: 4.6197. Min Act: -0.1700
Data Index: 1378130 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0572. Min Range: -5.0572
Max Act: 4.5572. Min Act: -0.1700
Data Index: 5766464 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0572. Min Range: -5.0572
Max Act: 4.5259. Min Act: -0.1700
Data Index: 8412115 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0572. Min Range: -5.0572
Max Act: 4.5259. Min Act: -0.1700
Data Index: 7855306 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0572. Min Range: -5.0572
Max Act: 4.5259. Min Act: -0.1700
Data Index: 5318651 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0572. Min Range: -5.0572
Max Act: 4.5259. Min Act: -0.1700
Data Index: 8087490 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0572. Min Range: -5.0572
Max Act: 4.4947. Min Act: -0.1700
Data Index: 3535465 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0572. Min Range: -5.0572
Max Act: 4.4947. Min Act: -0.1700
Data Index: 8412108 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0572. Min Range: -5.0572
Max Act: 4.4947. Min Act: -0.1700
Data Index: 4257627 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0572. Min Range: -5.0572
Max Act: 4.4947. Min Act: -0.1700
Data Index: 7753858 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0572. Min Range: -5.0572
Max Act: 4.4947. Min Act: -0.1700
Data Index: 2601695 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0572. Min Range: -5.0572
Max Act: 4.4947. Min Act: -0.1700
Data Index: 8685895 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0572. Min Range: -5.0572
Max Act: 4.4947. Min Act: -0.1700
Data Index: 4608528 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19