Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2698 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4351. Min Range: -6.4351
Max Act: 6.4351. Min Act: -0.1700
Data Index: 2159687 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4351. Min Range: -6.4351
Max Act: 6.3726. Min Act: -0.1700
Data Index: 3409680 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4351. Min Range: -6.4351
Max Act: 6.1851. Min Act: -0.1700
Data Index: 1957050 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4351. Min Range: -6.4351
Max Act: 6.1539. Min Act: -0.1700
Data Index: 4047168 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4351. Min Range: -6.4351
Max Act: 6.1226. Min Act: -0.1700
Data Index: 2498343 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4351. Min Range: -6.4351
Max Act: 6.0914. Min Act: -0.1700
Data Index: 6731588 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4351. Min Range: -6.4351
Max Act: 6.0601. Min Act: -0.1700
Data Index: 7399212 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4351. Min Range: -6.4351
Max Act: 6.0601. Min Act: -0.1700
Data Index: 2441637 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4351. Min Range: -6.4351
Max Act: 6.0289. Min Act: -0.1700
Data Index: 4910300 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4351. Min Range: -6.4351
Max Act: 6.0601. Min Act: -0.1700
Data Index: 7494639 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4351. Min Range: -6.4351
Max Act: 6.0289. Min Act: -0.1700
Data Index: 4248627 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4351. Min Range: -6.4351
Max Act: 5.9976. Min Act: -0.1700
Data Index: 1464789 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4351. Min Range: -6.4351
Max Act: 6.0289. Min Act: -0.1700
Data Index: 781542 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4351. Min Range: -6.4351
Max Act: 5.9976. Min Act: -0.1700
Data Index: 8580977 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4351. Min Range: -6.4351
Max Act: 5.9976. Min Act: -0.1700
Data Index: 7944794 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4351. Min Range: -6.4351
Max Act: 5.9664. Min Act: -0.1700
Data Index: 4425886 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4351. Min Range: -6.4351
Max Act: 5.9351. Min Act: -0.1700
Data Index: 1908430 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4351. Min Range: -6.4351
Max Act: 5.9039. Min Act: -0.1700
Data Index: 4447201 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4351. Min Range: -6.4351
Max Act: 5.9351. Min Act: -0.1700
Data Index: 2034788 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4351. Min Range: -6.4351
Max Act: 5.8726. Min Act: -0.1700
Data Index: 4504905 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19