Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2216 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7227. Min Range: -9.7227
Max Act: 9.7227. Min Act: -0.1700
Data Index: 4340874 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7227. Min Range: -9.7227
Max Act: 9.7227. Min Act: -0.1700
Data Index: 4340879 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7227. Min Range: -9.7227
Max Act: 9.4727. Min Act: -0.1700
Data Index: 4532631 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7227. Min Range: -9.7227
Max Act: 9.3477. Min Act: -0.1700
Data Index: 1789113 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7227. Min Range: -9.7227
Max Act: 9.2852. Min Act: -0.1700
Data Index: 5733848 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7227. Min Range: -9.7227
Max Act: 9.2227. Min Act: -0.1700
Data Index: 6025476 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7227. Min Range: -9.7227
Max Act: 9.2227. Min Act: -0.1700
Data Index: 5975096 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7227. Min Range: -9.7227
Max Act: 9.2227. Min Act: -0.1700
Data Index: 5721696 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7227. Min Range: -9.7227
Max Act: 9.1602. Min Act: -0.1700
Data Index: 8750635 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7227. Min Range: -9.7227
Max Act: 8.8477. Min Act: -0.1700
Data Index: 6054240 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7227. Min Range: -9.7227
Max Act: 8.9102. Min Act: -0.1700
Data Index: 480501 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7227. Min Range: -9.7227
Max Act: 8.8477. Min Act: -0.1700
Data Index: 8716228 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7227. Min Range: -9.7227
Max Act: 8.8477. Min Act: -0.1700
Data Index: 6619028 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7227. Min Range: -9.7227
Max Act: 8.8477. Min Act: -0.1700
Data Index: 4864172 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7227. Min Range: -9.7227
Max Act: 8.7852. Min Act: -0.1700
Data Index: 5870465 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7227. Min Range: -9.7227
Max Act: 8.7852. Min Act: -0.1700
Data Index: 1312782 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7227. Min Range: -9.7227
Max Act: 8.7852. Min Act: -0.1700
Data Index: 2174613 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7227. Min Range: -9.7227
Max Act: 8.7852. Min Act: -0.1700
Data Index: 1845032 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7227. Min Range: -9.7227
Max Act: 8.7227. Min Act: -0.1700
Data Index: 1344430 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7227. Min Range: -9.7227
Max Act: 8.7227. Min Act: -0.1700
Data Index: 1961312 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19