Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3668 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6978. Min Range: -2.6978
Max Act: 2.6978. Min Act: -0.1700
Data Index: 2069910 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6978. Min Range: -2.6978
Max Act: 2.6978. Min Act: -0.1700
Data Index: 3471828 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6978. Min Range: -2.6978
Max Act: 2.6337. Min Act: -0.1700
Data Index: 4353781 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6978. Min Range: -2.6978
Max Act: 2.6337. Min Act: -0.1700
Data Index: 533040 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6978. Min Range: -2.6978
Max Act: 2.6176. Min Act: -0.1700
Data Index: 2150822 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6978. Min Range: -2.6978
Max Act: 2.6015. Min Act: -0.1700
Data Index: 2811240 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6978. Min Range: -2.6978
Max Act: 2.5854. Min Act: -0.1700
Data Index: 7365838 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6978. Min Range: -2.6978
Max Act: 2.5854. Min Act: -0.1700
Data Index: 2970423 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6978. Min Range: -2.6978
Max Act: 2.5693. Min Act: -0.1700
Data Index: 2898445 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6978. Min Range: -2.6978
Max Act: 2.5693. Min Act: -0.1700
Data Index: 4465943 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6978. Min Range: -2.6978
Max Act: 2.5854. Min Act: -0.1700
Data Index: 125442 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6978. Min Range: -2.6978
Max Act: 2.5854. Min Act: -0.1700
Data Index: 6547976 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6978. Min Range: -2.6978
Max Act: 2.5532. Min Act: -0.1700
Data Index: 7136132 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6978. Min Range: -2.6978
Max Act: 2.5693. Min Act: -0.1700
Data Index: 3494450 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6978. Min Range: -2.6978
Max Act: 2.5693. Min Act: -0.1700
Data Index: 4849378 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6978. Min Range: -2.6978
Max Act: 2.5532. Min Act: -0.1700
Data Index: 2233884 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6978. Min Range: -2.6978
Max Act: 2.5854. Min Act: -0.1700
Data Index: 2889774 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6978. Min Range: -2.6978
Max Act: 2.5854. Min Act: -0.1700
Data Index: 1367054 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6978. Min Range: -2.6978
Max Act: 2.5854. Min Act: -0.1700
Data Index: 4895394 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6978. Min Range: -2.6978
Max Act: 2.5693. Min Act: -0.1700
Data Index: 4800186 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19