Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3176 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8663. Min Range: -5.8663
Max Act: 5.8663. Min Act: -0.1700
Data Index: 8118702 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8663. Min Range: -5.8663
Max Act: 5.8663. Min Act: -0.1700
Data Index: 6859824 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8663. Min Range: -5.8663
Max Act: 5.8038. Min Act: -0.1700
Data Index: 4259675 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8663. Min Range: -5.8663
Max Act: 5.8038. Min Act: -0.1700
Data Index: 3899485 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8663. Min Range: -5.8663
Max Act: 5.7726. Min Act: -0.1700
Data Index: 1108288 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8663. Min Range: -5.8663
Max Act: 5.7101. Min Act: -0.1700
Data Index: 1628341 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8663. Min Range: -5.8663
Max Act: 5.6788. Min Act: -0.1700
Data Index: 6877840 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8663. Min Range: -5.8663
Max Act: 5.7101. Min Act: -0.1700
Data Index: 580283 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8663. Min Range: -5.8663
Max Act: 5.7101. Min Act: -0.1700
Data Index: 1830760 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8663. Min Range: -5.8663
Max Act: 5.6476. Min Act: -0.1700
Data Index: 4488754 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8663. Min Range: -5.8663
Max Act: 5.6476. Min Act: -0.1700
Data Index: 4103273 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8663. Min Range: -5.8663
Max Act: 5.6476. Min Act: -0.1700
Data Index: 5486440 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8663. Min Range: -5.8663
Max Act: 5.6788. Min Act: -0.1700
Data Index: 7105942 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8663. Min Range: -5.8663
Max Act: 5.6476. Min Act: -0.1700
Data Index: 227561 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8663. Min Range: -5.8663
Max Act: 5.6163. Min Act: -0.1700
Data Index: 6877839 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8663. Min Range: -5.8663
Max Act: 5.6163. Min Act: -0.1700
Data Index: 2315153 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8663. Min Range: -5.8663
Max Act: 5.5851. Min Act: -0.1700
Data Index: 4115909 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8663. Min Range: -5.8663
Max Act: 5.5851. Min Act: -0.1700
Data Index: 4284677 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8663. Min Range: -5.8663
Max Act: 5.5851. Min Act: -0.1700
Data Index: 4274207 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8663. Min Range: -5.8663
Max Act: 5.5851. Min Act: -0.1700
Data Index: 7620451 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19