Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1823 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4229. Min Range: -5.4229
Max Act: 5.4229. Min Act: -0.1700
Data Index: 192727 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4229. Min Range: -5.4229
Max Act: 5.3916. Min Act: -0.1700
Data Index: 7688750 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4229. Min Range: -5.4229
Max Act: 5.3604. Min Act: -0.1700
Data Index: 7702410 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4229. Min Range: -5.4229
Max Act: 5.3291. Min Act: -0.1700
Data Index: 3402568 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4229. Min Range: -5.4229
Max Act: 5.2041. Min Act: -0.1700
Data Index: 2305298 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4229. Min Range: -5.4229
Max Act: 5.2354. Min Act: -0.1700
Data Index: 5231732 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4229. Min Range: -5.4229
Max Act: 5.1729. Min Act: -0.1700
Data Index: 3107926 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4229. Min Range: -5.4229
Max Act: 5.1416. Min Act: -0.1700
Data Index: 8528329 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4229. Min Range: -5.4229
Max Act: 5.1416. Min Act: -0.1700
Data Index: 1527391 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4229. Min Range: -5.4229
Max Act: 5.1416. Min Act: -0.1700
Data Index: 4361794 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4229. Min Range: -5.4229
Max Act: 5.1416. Min Act: -0.1700
Data Index: 259869 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4229. Min Range: -5.4229
Max Act: 5.1416. Min Act: -0.1700
Data Index: 46706 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4229. Min Range: -5.4229
Max Act: 5.1416. Min Act: -0.1700
Data Index: 4404854 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4229. Min Range: -5.4229
Max Act: 5.1104. Min Act: -0.1700
Data Index: 8654702 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4229. Min Range: -5.4229
Max Act: 5.1104. Min Act: -0.1700
Data Index: 1544869 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4229. Min Range: -5.4229
Max Act: 5.0479. Min Act: -0.1700
Data Index: 3004428 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4229. Min Range: -5.4229
Max Act: 5.0479. Min Act: -0.1700
Data Index: 3566634 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4229. Min Range: -5.4229
Max Act: 5.0479. Min Act: -0.1700
Data Index: 2951365 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4229. Min Range: -5.4229
Max Act: 5.0166. Min Act: -0.1700
Data Index: 449651 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4229. Min Range: -5.4229
Max Act: 5.0479. Min Act: -0.1700
Data Index: 7374780 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19