Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6373 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7163. Min Range: -5.7163
Max Act: 5.7163. Min Act: -0.1700
Data Index: 8054075 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7163. Min Range: -5.7163
Max Act: 5.6538. Min Act: -0.1700
Data Index: 7097823 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7163. Min Range: -5.7163
Max Act: 5.6226. Min Act: -0.1700
Data Index: 1709727 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7163. Min Range: -5.7163
Max Act: 5.5913. Min Act: -0.1700
Data Index: 7097820 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7163. Min Range: -5.7163
Max Act: 5.5913. Min Act: -0.1698
Data Index: 4102535 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7163. Min Range: -5.7163
Max Act: 5.5913. Min Act: -0.1700
Data Index: 6975362 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7163. Min Range: -5.7163
Max Act: 5.5601. Min Act: -0.1698
Data Index: 8048062 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7163. Min Range: -5.7163
Max Act: 5.5288. Min Act: -0.1699
Data Index: 4640581 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7163. Min Range: -5.7163
Max Act: 5.5288. Min Act: -0.1700
Data Index: 6570133 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7163. Min Range: -5.7163
Max Act: 5.5288. Min Act: -0.1700
Data Index: 6681020 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7163. Min Range: -5.7163
Max Act: 5.4976. Min Act: -0.1700
Data Index: 7097826 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7163. Min Range: -5.7163
Max Act: 5.4976. Min Act: -0.1700
Data Index: 677973 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7163. Min Range: -5.7163
Max Act: 5.4663. Min Act: -0.1700
Data Index: 7352089 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7163. Min Range: -5.7163
Max Act: 5.4663. Min Act: -0.1697
Data Index: 3748891 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7163. Min Range: -5.7163
Max Act: 5.4663. Min Act: -0.1700
Data Index: 7586641 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7163. Min Range: -5.7163
Max Act: 5.4351. Min Act: -0.1682
Data Index: 5637717 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7163. Min Range: -5.7163
Max Act: 5.4351. Min Act: -0.1700
Data Index: 1633367 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7163. Min Range: -5.7163
Max Act: 5.4351. Min Act: -0.1700
Data Index: 1621087 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7163. Min Range: -5.7163
Max Act: 5.4351. Min Act: -0.1700
Data Index: 128659 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7163. Min Range: -5.7163
Max Act: 5.4038. Min Act: -0.1700
Data Index: 3323436 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19