Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3260 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5251. Min Range: -4.5251
Max Act: 4.5251. Min Act: -0.1700
Data Index: 4676135 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5251. Min Range: -4.5251
Max Act: 4.2126. Min Act: -0.1700
Data Index: 533919 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5251. Min Range: -4.5251
Max Act: 4.1813. Min Act: -0.1700
Data Index: 4647109 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5251. Min Range: -4.5251
Max Act: 4.1813. Min Act: -0.1700
Data Index: 838831 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5251. Min Range: -4.5251
Max Act: 4.1188. Min Act: -0.1700
Data Index: 5378926 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5251. Min Range: -4.5251
Max Act: 4.1188. Min Act: -0.1700
Data Index: 3476725 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5251. Min Range: -4.5251
Max Act: 4.1188. Min Act: -0.1700
Data Index: 1836907 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5251. Min Range: -4.5251
Max Act: 4.0876. Min Act: -0.1700
Data Index: 185899 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5251. Min Range: -4.5251
Max Act: 4.0876. Min Act: -0.1700
Data Index: 6630469 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5251. Min Range: -4.5251
Max Act: 4.0251. Min Act: -0.1700
Data Index: 377275 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5251. Min Range: -4.5251
Max Act: 4.0251. Min Act: -0.1700
Data Index: 3825556 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5251. Min Range: -4.5251
Max Act: 4.0251. Min Act: -0.1700
Data Index: 6489005 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5251. Min Range: -4.5251
Max Act: 3.9938. Min Act: -0.1700
Data Index: 1575147 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5251. Min Range: -4.5251
Max Act: 3.9625. Min Act: -0.1700
Data Index: 8593125 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5251. Min Range: -4.5251
Max Act: 3.9938. Min Act: -0.1700
Data Index: 1081932 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5251. Min Range: -4.5251
Max Act: 3.9625. Min Act: -0.1700
Data Index: 1511263 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5251. Min Range: -4.5251
Max Act: 3.9625. Min Act: -0.1700
Data Index: 208596 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5251. Min Range: -4.5251
Max Act: 3.9938. Min Act: -0.1700
Data Index: 3369290 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5251. Min Range: -4.5251
Max Act: 3.9625. Min Act: -0.1700
Data Index: 7407053 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5251. Min Range: -4.5251
Max Act: 3.9625. Min Act: -0.1700
Data Index: 912984 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19