Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 857 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8757. Min Range: -4.8757
Max Act: 4.8444. Min Act: -0.1700
Data Index: 5220735 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8757. Min Range: -4.8757
Max Act: 4.8757. Min Act: -0.1700
Data Index: 3807147 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8757. Min Range: -4.8757
Max Act: 4.7819. Min Act: -0.1700
Data Index: 1963259 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8757. Min Range: -4.8757
Max Act: 4.8444. Min Act: -0.1700
Data Index: 4610177 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8757. Min Range: -4.8757
Max Act: 4.8132. Min Act: -0.1700
Data Index: 1516251 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8757. Min Range: -4.8757
Max Act: 4.8132. Min Act: -0.1700
Data Index: 2492901 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8757. Min Range: -4.8757
Max Act: 4.8132. Min Act: -0.1700
Data Index: 7845144 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8757. Min Range: -4.8757
Max Act: 4.7819. Min Act: -0.1700
Data Index: 3185692 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8757. Min Range: -4.8757
Max Act: 4.7507. Min Act: -0.1700
Data Index: 668103 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8757. Min Range: -4.8757
Max Act: 4.7507. Min Act: -0.1700
Data Index: 3491915 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8757. Min Range: -4.8757
Max Act: 4.7194. Min Act: -0.1700
Data Index: 79053 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8757. Min Range: -4.8757
Max Act: 4.7194. Min Act: -0.1700
Data Index: 2073085 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8757. Min Range: -4.8757
Max Act: 4.7507. Min Act: -0.1700
Data Index: 7530520 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8757. Min Range: -4.8757
Max Act: 4.6882. Min Act: -0.1700
Data Index: 3354401 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8757. Min Range: -4.8757
Max Act: 4.6569. Min Act: -0.1700
Data Index: 8646879 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8757. Min Range: -4.8757
Max Act: 4.6882. Min Act: -0.1700
Data Index: 4359745 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8757. Min Range: -4.8757
Max Act: 4.6882. Min Act: -0.1700
Data Index: 6145113 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8757. Min Range: -4.8757
Max Act: 4.6257. Min Act: -0.1700
Data Index: 7406916 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8757. Min Range: -4.8757
Max Act: 4.6569. Min Act: -0.1700
Data Index: 4443058 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8757. Min Range: -4.8757
Max Act: 4.6257. Min Act: -0.1700
Data Index: 772084 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19