Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1347 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2303. Min Range: -5.2303
Max Act: 5.2303. Min Act: -0.1700
Data Index: 6724885 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2303. Min Range: -5.2303
Max Act: 5.1678. Min Act: -0.1700
Data Index: 6583544 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2303. Min Range: -5.2303
Max Act: 5.0428. Min Act: -0.1700
Data Index: 1391627 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2303. Min Range: -5.2303
Max Act: 5.0115. Min Act: -0.1700
Data Index: 5152330 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2303. Min Range: -5.2303
Max Act: 4.9490. Min Act: -0.1700
Data Index: 5647315 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2303. Min Range: -5.2303
Max Act: 4.9490. Min Act: -0.1700
Data Index: 8058857 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2303. Min Range: -5.2303
Max Act: 4.9490. Min Act: -0.1700
Data Index: 5425067 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2303. Min Range: -5.2303
Max Act: 4.9490. Min Act: -0.1700
Data Index: 7053105 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2303. Min Range: -5.2303
Max Act: 4.9490. Min Act: -0.1700
Data Index: 41205 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2303. Min Range: -5.2303
Max Act: 4.9490. Min Act: -0.1700
Data Index: 5086871 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2303. Min Range: -5.2303
Max Act: 4.9803. Min Act: -0.1700
Data Index: 6627952 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2303. Min Range: -5.2303
Max Act: 4.9803. Min Act: -0.1700
Data Index: 1783982 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2303. Min Range: -5.2303
Max Act: 4.9490. Min Act: -0.1700
Data Index: 5656622 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2303. Min Range: -5.2303
Max Act: 4.9178. Min Act: -0.1700
Data Index: 599999 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2303. Min Range: -5.2303
Max Act: 4.9178. Min Act: -0.1700
Data Index: 260805 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2303. Min Range: -5.2303
Max Act: 4.9178. Min Act: -0.1700
Data Index: 4642525 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2303. Min Range: -5.2303
Max Act: 4.8553. Min Act: -0.1700
Data Index: 6445029 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2303. Min Range: -5.2303
Max Act: 4.8553. Min Act: -0.1700
Data Index: 6142617 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2303. Min Range: -5.2303
Max Act: 4.8240. Min Act: -0.1700
Data Index: 600072 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2303. Min Range: -5.2303
Max Act: 4.8553. Min Act: -0.1700
Data Index: 1033459 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19