Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2869 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2034. Min Range: -6.2034
Max Act: 6.2034. Min Act: -0.1700
Data Index: 4197953 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2034. Min Range: -6.2034
Max Act: 6.1721. Min Act: -0.1700
Data Index: 8545919 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2034. Min Range: -6.2034
Max Act: 6.1409. Min Act: -0.1700
Data Index: 730016 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2034. Min Range: -6.2034
Max Act: 6.1409. Min Act: -0.1700
Data Index: 978343 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2034. Min Range: -6.2034
Max Act: 6.1409. Min Act: -0.1700
Data Index: 1687329 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2034. Min Range: -6.2034
Max Act: 6.1096. Min Act: -0.1700
Data Index: 908319 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2034. Min Range: -6.2034
Max Act: 6.0471. Min Act: -0.1700
Data Index: 8646456 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2034. Min Range: -6.2034
Max Act: 6.0159. Min Act: -0.1700
Data Index: 6929363 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2034. Min Range: -6.2034
Max Act: 5.9846. Min Act: -0.1700
Data Index: 2782912 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2034. Min Range: -6.2034
Max Act: 5.9846. Min Act: -0.1700
Data Index: 8144097 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2034. Min Range: -6.2034
Max Act: 5.9534. Min Act: -0.1700
Data Index: 7025927 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2034. Min Range: -6.2034
Max Act: 5.9534. Min Act: -0.1700
Data Index: 7429560 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2034. Min Range: -6.2034
Max Act: 5.9534. Min Act: -0.1700
Data Index: 8718577 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2034. Min Range: -6.2034
Max Act: 5.9534. Min Act: -0.1700
Data Index: 3076400 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2034. Min Range: -6.2034
Max Act: 5.9534. Min Act: -0.1700
Data Index: 2803366 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2034. Min Range: -6.2034
Max Act: 5.9534. Min Act: -0.1700
Data Index: 8685716 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2034. Min Range: -6.2034
Max Act: 5.9534. Min Act: -0.1700
Data Index: 667546 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2034. Min Range: -6.2034
Max Act: 5.9221. Min Act: -0.1700
Data Index: 857864 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2034. Min Range: -6.2034
Max Act: 5.9221. Min Act: -0.1700
Data Index: 6736848 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2034. Min Range: -6.2034
Max Act: 5.9221. Min Act: -0.1700
Data Index: 4135884 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19