Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 35 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1557. Min Range: -5.1557
Max Act: 5.1557. Min Act: -0.1700
Data Index: 6026509 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1557. Min Range: -5.1557
Max Act: 5.1244. Min Act: -0.1700
Data Index: 4991000 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1557. Min Range: -5.1557
Max Act: 5.1244. Min Act: -0.1700
Data Index: 1074389 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1557. Min Range: -5.1557
Max Act: 5.1244. Min Act: -0.1700
Data Index: 3801320 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1557. Min Range: -5.1557
Max Act: 5.1244. Min Act: -0.1700
Data Index: 238017 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1557. Min Range: -5.1557
Max Act: 5.1244. Min Act: -0.1700
Data Index: 8172274 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1557. Min Range: -5.1557
Max Act: 5.1557. Min Act: -0.1700
Data Index: 3288905 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1557. Min Range: -5.1557
Max Act: 5.0932. Min Act: -0.1700
Data Index: 2985515 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1557. Min Range: -5.1557
Max Act: 5.0932. Min Act: -0.1700
Data Index: 831233 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1557. Min Range: -5.1557
Max Act: 5.0619. Min Act: -0.1700
Data Index: 6725787 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1557. Min Range: -5.1557
Max Act: 5.0619. Min Act: -0.1700
Data Index: 1821310 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1557. Min Range: -5.1557
Max Act: 5.0619. Min Act: -0.1700
Data Index: 1865816 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1557. Min Range: -5.1557
Max Act: 5.0619. Min Act: -0.1700
Data Index: 7560887 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1557. Min Range: -5.1557
Max Act: 5.0619. Min Act: -0.1700
Data Index: 1787780 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1557. Min Range: -5.1557
Max Act: 5.0619. Min Act: -0.1700
Data Index: 8568620 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1557. Min Range: -5.1557
Max Act: 5.0619. Min Act: -0.1700
Data Index: 308560 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1557. Min Range: -5.1557
Max Act: 5.0619. Min Act: -0.1700
Data Index: 454974 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1557. Min Range: -5.1557
Max Act: 5.0307. Min Act: -0.1700
Data Index: 1586822 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1557. Min Range: -5.1557
Max Act: 4.9994. Min Act: -0.1700
Data Index: 2800725 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1557. Min Range: -5.1557
Max Act: 5.0307. Min Act: -0.1700
Data Index: 354940 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19