Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 878 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3760. Min Range: -5.3760
Max Act: 5.3760. Min Act: -0.1700
Data Index: 5054704 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3760. Min Range: -5.3760
Max Act: 5.2198. Min Act: -0.1700
Data Index: 1867601 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3760. Min Range: -5.3760
Max Act: 5.1885. Min Act: -0.1700
Data Index: 803997 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3760. Min Range: -5.3760
Max Act: 5.1573. Min Act: -0.1700
Data Index: 2090241 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3760. Min Range: -5.3760
Max Act: 5.1573. Min Act: -0.1700
Data Index: 3090320 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3760. Min Range: -5.3760
Max Act: 5.1573. Min Act: -0.1700
Data Index: 5858084 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3760. Min Range: -5.3760
Max Act: 5.0635. Min Act: -0.1700
Data Index: 4015508 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3760. Min Range: -5.3760
Max Act: 5.0635. Min Act: -0.1700
Data Index: 2221381 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3760. Min Range: -5.3760
Max Act: 5.0635. Min Act: -0.1700
Data Index: 4051578 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3760. Min Range: -5.3760
Max Act: 5.0635. Min Act: -0.1700
Data Index: 1623449 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3760. Min Range: -5.3760
Max Act: 5.0635. Min Act: -0.1700
Data Index: 55271 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3760. Min Range: -5.3760
Max Act: 5.0323. Min Act: -0.1700
Data Index: 822571 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3760. Min Range: -5.3760
Max Act: 5.0323. Min Act: -0.1700
Data Index: 3656487 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3760. Min Range: -5.3760
Max Act: 5.0323. Min Act: -0.1700
Data Index: 6148664 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3760. Min Range: -5.3760
Max Act: 5.0323. Min Act: -0.1700
Data Index: 6759022 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3760. Min Range: -5.3760
Max Act: 5.0323. Min Act: -0.1700
Data Index: 803996 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3760. Min Range: -5.3760
Max Act: 5.0010. Min Act: -0.1700
Data Index: 5219097 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3760. Min Range: -5.3760
Max Act: 5.0010. Min Act: -0.1700
Data Index: 3947259 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3760. Min Range: -5.3760
Max Act: 5.0010. Min Act: -0.1700
Data Index: 3688267 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3760. Min Range: -5.3760
Max Act: 5.0010. Min Act: -0.1700
Data Index: 6407058 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19