Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1678 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9649. Min Range: -4.9649
Max Act: 4.9649. Min Act: -0.1700
Data Index: 1094036 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9649. Min Range: -4.9649
Max Act: 4.9649. Min Act: -0.1700
Data Index: 1804640 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9649. Min Range: -4.9649
Max Act: 4.9337. Min Act: -0.1700
Data Index: 7405298 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9649. Min Range: -4.9649
Max Act: 4.9024. Min Act: -0.1700
Data Index: 4038426 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9649. Min Range: -4.9649
Max Act: 4.8712. Min Act: -0.1700
Data Index: 1696341 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9649. Min Range: -4.9649
Max Act: 4.8399. Min Act: -0.1700
Data Index: 6186815 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9649. Min Range: -4.9649
Max Act: 4.8087. Min Act: -0.1700
Data Index: 4051130 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9649. Min Range: -4.9649
Max Act: 4.8399. Min Act: -0.1700
Data Index: 8788487 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9649. Min Range: -4.9649
Max Act: 4.7774. Min Act: -0.1700
Data Index: 2762647 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9649. Min Range: -4.9649
Max Act: 4.5586. Min Act: -0.1700
Data Index: 3335250 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9649. Min Range: -4.9649
Max Act: 4.4961. Min Act: -0.1700
Data Index: 1232769 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9649. Min Range: -4.9649
Max Act: 4.4961. Min Act: -0.1700
Data Index: 7124581 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9649. Min Range: -4.9649
Max Act: 4.4649. Min Act: -0.1700
Data Index: 3177607 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9649. Min Range: -4.9649
Max Act: 4.4649. Min Act: -0.1700
Data Index: 698515 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9649. Min Range: -4.9649
Max Act: 4.4649. Min Act: -0.1700
Data Index: 1790815 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9649. Min Range: -4.9649
Max Act: 4.4649. Min Act: -0.1700
Data Index: 7451330 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9649. Min Range: -4.9649
Max Act: 4.4336. Min Act: -0.1700
Data Index: 8198580 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9649. Min Range: -4.9649
Max Act: 4.3711. Min Act: -0.1700
Data Index: 3196667 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9649. Min Range: -4.9649
Max Act: 4.4024. Min Act: -0.1700
Data Index: 5841491 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9649. Min Range: -4.9649
Max Act: 4.4024. Min Act: -0.1700
Data Index: 2631484 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19