Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1860 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6333. Min Range: -9.6333
Max Act: 9.6333. Min Act: -0.1700
Data Index: 3308276 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6333. Min Range: -9.6333
Max Act: 9.5708. Min Act: -0.1700
Data Index: 5320044 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6333. Min Range: -9.6333
Max Act: 9.3208. Min Act: -0.1700
Data Index: 6063855 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6333. Min Range: -9.6333
Max Act: 9.3208. Min Act: -0.1700
Data Index: 8239465 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6333. Min Range: -9.6333
Max Act: 9.2583. Min Act: -0.1700
Data Index: 3513276 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6333. Min Range: -9.6333
Max Act: 9.2583. Min Act: -0.1700
Data Index: 2883263 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6333. Min Range: -9.6333
Max Act: 9.2583. Min Act: -0.1700
Data Index: 2580155 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6333. Min Range: -9.6333
Max Act: 9.2583. Min Act: -0.1700
Data Index: 1545547 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6333. Min Range: -9.6333
Max Act: 9.2583. Min Act: -0.1700
Data Index: 2537714 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6333. Min Range: -9.6333
Max Act: 9.2583. Min Act: -0.1700
Data Index: 369785 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6333. Min Range: -9.6333
Max Act: 9.1958. Min Act: -0.1700
Data Index: 5907602 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6333. Min Range: -9.6333
Max Act: 9.1958. Min Act: -0.1700
Data Index: 3336223 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6333. Min Range: -9.6333
Max Act: 9.1958. Min Act: -0.1700
Data Index: 4249601 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6333. Min Range: -9.6333
Max Act: 9.1958. Min Act: -0.1700
Data Index: 4309607 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6333. Min Range: -9.6333
Max Act: 9.1958. Min Act: -0.1700
Data Index: 3011598 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6333. Min Range: -9.6333
Max Act: 9.1958. Min Act: -0.1700
Data Index: 4636436 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6333. Min Range: -9.6333
Max Act: 9.1333. Min Act: -0.1700
Data Index: 614731 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6333. Min Range: -9.6333
Max Act: 9.1333. Min Act: -0.1700
Data Index: 6006797 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6333. Min Range: -9.6333
Max Act: 9.1333. Min Act: -0.1700
Data Index: 3564741 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6333. Min Range: -9.6333
Max Act: 9.1333. Min Act: -0.1700
Data Index: 4429569 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19