Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3024 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1084. Min Range: -7.1084
Max Act: 7.1084. Min Act: -0.1700
Data Index: 4855881 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1084. Min Range: -7.1084
Max Act: 6.9834. Min Act: -0.1700
Data Index: 643646 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1084. Min Range: -7.1084
Max Act: 6.9522. Min Act: -0.1700
Data Index: 1927707 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1084. Min Range: -7.1084
Max Act: 6.8897. Min Act: -0.1700
Data Index: 4855891 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1084. Min Range: -7.1084
Max Act: 6.9522. Min Act: -0.1700
Data Index: 309287 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1084. Min Range: -7.1084
Max Act: 6.9522. Min Act: -0.1700
Data Index: 6980514 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1084. Min Range: -7.1084
Max Act: 6.8584. Min Act: -0.1700
Data Index: 6141200 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1084. Min Range: -7.1084
Max Act: 6.8584. Min Act: -0.1700
Data Index: 2036995 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1084. Min Range: -7.1084
Max Act: 6.7959. Min Act: -0.1700
Data Index: 6722225 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1084. Min Range: -7.1084
Max Act: 6.7647. Min Act: -0.1700
Data Index: 7553513 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1084. Min Range: -7.1084
Max Act: 6.7334. Min Act: -0.1700
Data Index: 7294925 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1084. Min Range: -7.1084
Max Act: 6.7334. Min Act: -0.1700
Data Index: 3523950 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1084. Min Range: -7.1084
Max Act: 6.7022. Min Act: -0.1700
Data Index: 4855899 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1084. Min Range: -7.1084
Max Act: 6.7334. Min Act: -0.1700
Data Index: 7973720 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1084. Min Range: -7.1084
Max Act: 6.7334. Min Act: -0.1700
Data Index: 2056414 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1084. Min Range: -7.1084
Max Act: 6.7334. Min Act: -0.1700
Data Index: 3086612 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1084. Min Range: -7.1084
Max Act: 6.6709. Min Act: -0.1700
Data Index: 7973721 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1084. Min Range: -7.1084
Max Act: 6.6397. Min Act: -0.1700
Data Index: 3791273 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1084. Min Range: -7.1084
Max Act: 6.6709. Min Act: -0.1700
Data Index: 4650004 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1084. Min Range: -7.1084
Max Act: 6.7022. Min Act: -0.1700
Data Index: 1915103 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19