Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3577 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3065. Min Range: -8.3065
Max Act: 8.3065. Min Act: -0.1700
Data Index: 4795152 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3065. Min Range: -8.3065
Max Act: 8.1815. Min Act: -0.1700
Data Index: 2057399 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3065. Min Range: -8.3065
Max Act: 8.0565. Min Act: -0.1700
Data Index: 6874521 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3065. Min Range: -8.3065
Max Act: 7.9940. Min Act: -0.1700
Data Index: 181282 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3065. Min Range: -8.3065
Max Act: 7.9940. Min Act: -0.1700
Data Index: 118136 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3065. Min Range: -8.3065
Max Act: 7.9315. Min Act: -0.1700
Data Index: 2998150 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3065. Min Range: -8.3065
Max Act: 7.9315. Min Act: -0.1700
Data Index: 4180322 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3065. Min Range: -8.3065
Max Act: 7.8065. Min Act: -0.1700
Data Index: 7443669 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3065. Min Range: -8.3065
Max Act: 7.8065. Min Act: -0.1700
Data Index: 7500519 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3065. Min Range: -8.3065
Max Act: 7.8065. Min Act: -0.1700
Data Index: 2502940 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3065. Min Range: -8.3065
Max Act: 7.8065. Min Act: -0.1700
Data Index: 1259583 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3065. Min Range: -8.3065
Max Act: 7.7128. Min Act: -0.1700
Data Index: 6980481 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3065. Min Range: -8.3065
Max Act: 7.7128. Min Act: -0.1700
Data Index: 4150938 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3065. Min Range: -8.3065
Max Act: 7.6503. Min Act: -0.1700
Data Index: 3457600 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3065. Min Range: -8.3065
Max Act: 7.6503. Min Act: -0.1700
Data Index: 7119625 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3065. Min Range: -8.3065
Max Act: 7.6503. Min Act: -0.1700
Data Index: 6651786 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3065. Min Range: -8.3065
Max Act: 7.5878. Min Act: -0.1700
Data Index: 3828970 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3065. Min Range: -8.3065
Max Act: 7.5878. Min Act: -0.1700
Data Index: 6170926 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3065. Min Range: -8.3065
Max Act: 7.5878. Min Act: -0.1700
Data Index: 1151597 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3065. Min Range: -8.3065
Max Act: 7.5878. Min Act: -0.1700
Data Index: 3679652 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19