Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3063 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3252. Min Range: -5.3252
Max Act: 5.2940. Min Act: -0.1700
Data Index: 7502862 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3252. Min Range: -5.3252
Max Act: 5.3252. Min Act: -0.1700
Data Index: 4459542 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3252. Min Range: -5.3252
Max Act: 5.3252. Min Act: -0.1700
Data Index: 5137142 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3252. Min Range: -5.3252
Max Act: 5.3252. Min Act: -0.1700
Data Index: 6033615 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3252. Min Range: -5.3252
Max Act: 5.2627. Min Act: -0.1700
Data Index: 5197574 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3252. Min Range: -5.3252
Max Act: 5.2315. Min Act: -0.1700
Data Index: 8291153 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3252. Min Range: -5.3252
Max Act: 5.2627. Min Act: -0.1700
Data Index: 8010232 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3252. Min Range: -5.3252
Max Act: 5.2627. Min Act: -0.1700
Data Index: 3415511 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3252. Min Range: -5.3252
Max Act: 5.2627. Min Act: -0.1700
Data Index: 3962983 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3252. Min Range: -5.3252
Max Act: 5.2627. Min Act: -0.1700
Data Index: 2527972 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3252. Min Range: -5.3252
Max Act: 5.2627. Min Act: -0.1700
Data Index: 3286210 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3252. Min Range: -5.3252
Max Act: 5.2002. Min Act: -0.1700
Data Index: 2054263 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3252. Min Range: -5.3252
Max Act: 5.2315. Min Act: -0.1700
Data Index: 3411891 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3252. Min Range: -5.3252
Max Act: 5.2315. Min Act: -0.1700
Data Index: 503291 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3252. Min Range: -5.3252
Max Act: 5.2315. Min Act: -0.1700
Data Index: 3346086 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3252. Min Range: -5.3252
Max Act: 5.2315. Min Act: -0.1700
Data Index: 2400443 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3252. Min Range: -5.3252
Max Act: 5.2315. Min Act: -0.1700
Data Index: 946099 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3252. Min Range: -5.3252
Max Act: 5.2315. Min Act: -0.1700
Data Index: 2409377 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3252. Min Range: -5.3252
Max Act: 5.2315. Min Act: -0.1700
Data Index: 1308467 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3252. Min Range: -5.3252
Max Act: 5.2315. Min Act: -0.1700
Data Index: 3536979 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19