Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1769 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7553. Min Range: -3.7553
Max Act: 3.7553. Min Act: -0.1700
Data Index: 4904485 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7553. Min Range: -3.7553
Max Act: 3.6927. Min Act: -0.1700
Data Index: 7627121 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7553. Min Range: -3.7553
Max Act: 3.6771. Min Act: -0.1700
Data Index: 4720745 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7553. Min Range: -3.7553
Max Act: 3.6927. Min Act: -0.1700
Data Index: 6840893 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7553. Min Range: -3.7553
Max Act: 3.6771. Min Act: -0.1700
Data Index: 5085224 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7553. Min Range: -3.7553
Max Act: 3.6458. Min Act: -0.1700
Data Index: 1195264 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7553. Min Range: -3.7553
Max Act: 3.6301. Min Act: -0.1700
Data Index: 1509889 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7553. Min Range: -3.7553
Max Act: 3.6301. Min Act: -0.1700
Data Index: 647169 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7553. Min Range: -3.7553
Max Act: 3.6145. Min Act: -0.1700
Data Index: 3059549 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7553. Min Range: -3.7553
Max Act: 3.6145. Min Act: -0.1700
Data Index: 5476787 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7553. Min Range: -3.7553
Max Act: 3.5988. Min Act: -0.1700
Data Index: 3923860 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7553. Min Range: -3.7553
Max Act: 3.6145. Min Act: -0.1700
Data Index: 1353236 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7553. Min Range: -3.7553
Max Act: 3.5832. Min Act: -0.1700
Data Index: 1366344 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7553. Min Range: -3.7553
Max Act: 3.6145. Min Act: -0.1700
Data Index: 1079218 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7553. Min Range: -3.7553
Max Act: 3.5675. Min Act: -0.1700
Data Index: 7084336 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7553. Min Range: -3.7553
Max Act: 3.5675. Min Act: -0.1700
Data Index: 4851069 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7553. Min Range: -3.7553
Max Act: 3.5362. Min Act: -0.1700
Data Index: 2340194 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7553. Min Range: -3.7553
Max Act: 3.5519. Min Act: -0.1700
Data Index: 5535597 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7553. Min Range: -3.7553
Max Act: 3.5205. Min Act: -0.1700
Data Index: 4892524 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7553. Min Range: -3.7553
Max Act: 3.5362. Min Act: -0.1700
Data Index: 5593066 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #19