Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1521 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3396. Min Range: -4.3396
Max Act: 4.3396. Min Act: -0.1700
Data Index: 3316204 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3396. Min Range: -4.3396
Max Act: 4.0271. Min Act: -0.1700
Data Index: 5928850 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3396. Min Range: -4.3396
Max Act: 4.0271. Min Act: -0.1700
Data Index: 5647736 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3396. Min Range: -4.3396
Max Act: 3.9958. Min Act: -0.1700
Data Index: 1072409 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3396. Min Range: -4.3396
Max Act: 3.9646. Min Act: -0.1700
Data Index: 2634131 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3396. Min Range: -4.3396
Max Act: 3.9333. Min Act: -0.1700
Data Index: 394874 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3396. Min Range: -4.3396
Max Act: 3.9333. Min Act: -0.1700
Data Index: 3574981 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3396. Min Range: -4.3396
Max Act: 3.9333. Min Act: -0.1700
Data Index: 2158684 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3396. Min Range: -4.3396
Max Act: 3.9020. Min Act: -0.1700
Data Index: 7193271 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3396. Min Range: -4.3396
Max Act: 3.9020. Min Act: -0.1700
Data Index: 5078794 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3396. Min Range: -4.3396
Max Act: 3.8708. Min Act: -0.1700
Data Index: 4442827 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3396. Min Range: -4.3396
Max Act: 3.9020. Min Act: -0.1700
Data Index: 8675659 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3396. Min Range: -4.3396
Max Act: 3.8708. Min Act: -0.1700
Data Index: 8164622 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3396. Min Range: -4.3396
Max Act: 3.8395. Min Act: -0.1700
Data Index: 8174322 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3396. Min Range: -4.3396
Max Act: 3.8708. Min Act: -0.1700
Data Index: 7741043 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3396. Min Range: -4.3396
Max Act: 3.8708. Min Act: -0.1700
Data Index: 3574975 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3396. Min Range: -4.3396
Max Act: 3.9020. Min Act: -0.1700
Data Index: 6847126 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3396. Min Range: -4.3396
Max Act: 3.8708. Min Act: -0.1700
Data Index: 1050700 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3396. Min Range: -4.3396
Max Act: 3.8395. Min Act: -0.1700
Data Index: 8426413 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3396. Min Range: -4.3396
Max Act: 3.8708. Min Act: -0.1700
Data Index: 5804316 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19