Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1045 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9146. Min Range: -1.9146
Max Act: 1.9146. Min Act: -0.1700
Data Index: 4409343 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9146. Min Range: -1.9146
Max Act: 1.8463. Min Act: -0.1700
Data Index: 118678 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9146. Min Range: -1.9146
Max Act: 1.7948. Min Act: -0.1699
Data Index: 4720587 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9146. Min Range: -1.9146
Max Act: 1.8120. Min Act: -0.1700
Data Index: 1315946 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9146. Min Range: -1.9146
Max Act: 1.7430. Min Act: -0.1700
Data Index: 118671 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9146. Min Range: -1.9146
Max Act: 1.7257. Min Act: -0.1700
Data Index: 6976024 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9146. Min Range: -1.9146
Max Act: 1.7257. Min Act: -0.1699
Data Index: 118685 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9146. Min Range: -1.9146
Max Act: 1.6911. Min Act: -0.1700
Data Index: 3526993 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9146. Min Range: -1.9146
Max Act: 1.7084. Min Act: -0.1700
Data Index: 3669110 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9146. Min Range: -1.9146
Max Act: 1.7084. Min Act: -0.1699
Data Index: 5091811 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9146. Min Range: -1.9146
Max Act: 1.7084. Min Act: -0.1695
Data Index: 1288693 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9146. Min Range: -1.9146
Max Act: 1.7084. Min Act: -0.1700
Data Index: 118687 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9146. Min Range: -1.9146
Max Act: 1.6737. Min Act: -0.1700
Data Index: 2376336 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9146. Min Range: -1.9146
Max Act: 1.6737. Min Act: -0.1700
Data Index: 446213 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9146. Min Range: -1.9146
Max Act: 1.6563. Min Act: -0.1700
Data Index: 7304771 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9146. Min Range: -1.9146
Max Act: 1.6563. Min Act: -0.1700
Data Index: 795313 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9146. Min Range: -1.9146
Max Act: 1.6563. Min Act: -0.1700
Data Index: 972474 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9146. Min Range: -1.9146
Max Act: 1.6737. Min Act: -0.1700
Data Index: 6441280 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9146. Min Range: -1.9146
Max Act: 1.6389. Min Act: -0.1697
Data Index: 3162866 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9146. Min Range: -1.9146
Max Act: 1.6389. Min Act: -0.1700
Data Index: 5677104 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19