Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3571 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.7374. Min Act: -0.1700
Data Index: 4731659 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.7061. Min Act: -0.1700
Data Index: 4406793 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.6749. Min Act: -0.1700
Data Index: 7866279 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.5811. Min Act: -0.1700
Data Index: 238774 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.4874. Min Act: -0.1700
Data Index: 1396530 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.4874. Min Act: -0.1700
Data Index: 7458135 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.4249. Min Act: -0.1700
Data Index: 8637808 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.4561. Min Act: -0.1700
Data Index: 3065332 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.4561. Min Act: -0.1700
Data Index: 6960764 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.4249. Min Act: -0.1700
Data Index: 7611104 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.4561. Min Act: -0.1700
Data Index: 2066365 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.3936. Min Act: -0.1700
Data Index: 7951063 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.3936. Min Act: -0.1700
Data Index: 780527 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.3936. Min Act: -0.1700
Data Index: 2878904 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.3936. Min Act: -0.1700
Data Index: 8831081 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.3624. Min Act: -0.1700
Data Index: 6592667 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.3624. Min Act: -0.1700
Data Index: 8004367 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.3624. Min Act: -0.1700
Data Index: 2558870 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.3624. Min Act: -0.1700
Data Index: 1877006 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.3311. Min Act: -0.1700
Data Index: 6061020 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19