Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3768 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8770. Min Range: -8.8770
Max Act: 8.8770. Min Act: -0.1700
Data Index: 1767324 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8770. Min Range: -8.8770
Max Act: 8.2520. Min Act: -0.1700
Data Index: 6443683 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8770. Min Range: -8.8770
Max Act: 8.0020. Min Act: -0.1700
Data Index: 6192243 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8770. Min Range: -8.8770
Max Act: 7.9395. Min Act: -0.1700
Data Index: 2090936 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8770. Min Range: -8.8770
Max Act: 7.6270. Min Act: -0.1700
Data Index: 6264216 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8770. Min Range: -8.8770
Max Act: 7.6270. Min Act: -0.1700
Data Index: 1279842 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8770. Min Range: -8.8770
Max Act: 7.6270. Min Act: -0.1700
Data Index: 1885940 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8770. Min Range: -8.8770
Max Act: 7.6270. Min Act: -0.1700
Data Index: 4771168 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8770. Min Range: -8.8770
Max Act: 7.5958. Min Act: -0.1700
Data Index: 3767306 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8770. Min Range: -8.8770
Max Act: 7.5958. Min Act: -0.1700
Data Index: 2513791 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8770. Min Range: -8.8770
Max Act: 7.5645. Min Act: -0.1700
Data Index: 5187086 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8770. Min Range: -8.8770
Max Act: 7.5333. Min Act: -0.1700
Data Index: 790659 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8770. Min Range: -8.8770
Max Act: 7.4708. Min Act: -0.1700
Data Index: 5144239 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8770. Min Range: -8.8770
Max Act: 7.5020. Min Act: -0.1700
Data Index: 2114537 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8770. Min Range: -8.8770
Max Act: 7.5333. Min Act: -0.1700
Data Index: 6555874 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8770. Min Range: -8.8770
Max Act: 7.4708. Min Act: -0.1700
Data Index: 8366227 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8770. Min Range: -8.8770
Max Act: 7.4708. Min Act: -0.1700
Data Index: 973425 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8770. Min Range: -8.8770
Max Act: 7.4708. Min Act: -0.1700
Data Index: 3447332 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8770. Min Range: -8.8770
Max Act: 7.4395. Min Act: -0.1700
Data Index: 2793552 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8770. Min Range: -8.8770
Max Act: 7.4083. Min Act: -0.1700
Data Index: 2371207 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19