Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4085 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7439. Min Range: -3.7439
Max Act: 3.7439. Min Act: -0.1700
Data Index: 2658908 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7439. Min Range: -3.7439
Max Act: 3.6657. Min Act: -0.1700
Data Index: 7252678 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7439. Min Range: -3.7439
Max Act: 3.6657. Min Act: -0.1700
Data Index: 3090844 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7439. Min Range: -3.7439
Max Act: 3.6500. Min Act: -0.1700
Data Index: 1180324 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7439. Min Range: -3.7439
Max Act: 3.6344. Min Act: -0.1700
Data Index: 976756 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7439. Min Range: -3.7439
Max Act: 3.5874. Min Act: -0.1700
Data Index: 10090 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7439. Min Range: -3.7439
Max Act: 3.5874. Min Act: -0.1700
Data Index: 484431 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7439. Min Range: -3.7439
Max Act: 3.5718. Min Act: -0.1700
Data Index: 7257779 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7439. Min Range: -3.7439
Max Act: 3.5718. Min Act: -0.1700
Data Index: 4935269 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7439. Min Range: -3.7439
Max Act: 3.5561. Min Act: -0.1700
Data Index: 5664380 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7439. Min Range: -3.7439
Max Act: 3.5405. Min Act: -0.1700
Data Index: 5971912 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7439. Min Range: -3.7439
Max Act: 3.5248. Min Act: -0.1700
Data Index: 558894 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7439. Min Range: -3.7439
Max Act: 3.5248. Min Act: -0.1700
Data Index: 4367081 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7439. Min Range: -3.7439
Max Act: 3.4935. Min Act: -0.1700
Data Index: 1304455 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7439. Min Range: -3.7439
Max Act: 3.4778. Min Act: -0.1700
Data Index: 3698164 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7439. Min Range: -3.7439
Max Act: 3.4935. Min Act: -0.1700
Data Index: 1031680 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7439. Min Range: -3.7439
Max Act: 3.5091. Min Act: -0.1700
Data Index: 2303314 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7439. Min Range: -3.7439
Max Act: 3.4935. Min Act: -0.1700
Data Index: 7179896 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7439. Min Range: -3.7439
Max Act: 3.5091. Min Act: -0.1700
Data Index: 6924359 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7439. Min Range: -3.7439
Max Act: 3.5091. Min Act: -0.1700
Data Index: 2216202 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19