Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2676 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1252. Min Range: -3.1252
Max Act: 3.1252. Min Act: -0.1700
Data Index: 1626798 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1252. Min Range: -3.1252
Max Act: 3.0779. Min Act: -0.1700
Data Index: 5741903 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1252. Min Range: -3.1252
Max Act: 3.0936. Min Act: -0.1700
Data Index: 5325170 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1252. Min Range: -3.1252
Max Act: 3.0779. Min Act: -0.1700
Data Index: 3973045 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1252. Min Range: -3.1252
Max Act: 3.0621. Min Act: -0.1700
Data Index: 7718727 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1252. Min Range: -3.1252
Max Act: 2.9989. Min Act: -0.1700
Data Index: 540976 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1252. Min Range: -3.1252
Max Act: 2.9989. Min Act: -0.1700
Data Index: 7831472 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1252. Min Range: -3.1252
Max Act: 2.9357. Min Act: -0.1700
Data Index: 540985 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1252. Min Range: -3.1252
Max Act: 2.9357. Min Act: -0.1700
Data Index: 5606163 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1252. Min Range: -3.1252
Max Act: 2.9357. Min Act: -0.1700
Data Index: 8474822 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1252. Min Range: -3.1252
Max Act: 2.9198. Min Act: -0.1700
Data Index: 4205822 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1252. Min Range: -3.1252
Max Act: 2.9198. Min Act: -0.1700
Data Index: 540979 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1252. Min Range: -3.1252
Max Act: 2.9040. Min Act: -0.1700
Data Index: 7525763 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1252. Min Range: -3.1252
Max Act: 2.8881. Min Act: -0.1700
Data Index: 6604817 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1252. Min Range: -3.1252
Max Act: 2.9040. Min Act: -0.1700
Data Index: 6577968 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1252. Min Range: -3.1252
Max Act: 2.9040. Min Act: -0.1700
Data Index: 6938973 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1252. Min Range: -3.1252
Max Act: 2.9040. Min Act: -0.1700
Data Index: 540987 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1252. Min Range: -3.1252
Max Act: 2.9040. Min Act: -0.1700
Data Index: 540980 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1252. Min Range: -3.1252
Max Act: 2.9040. Min Act: -0.1700
Data Index: 6841797 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1252. Min Range: -3.1252
Max Act: 2.9040. Min Act: -0.1700
Data Index: 4211220 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19