Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2349. Min Range: -5.2349
Max Act: 5.2349. Min Act: -0.1700
Data Index: 113702 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2349. Min Range: -5.2349
Max Act: 5.1412. Min Act: -0.1700
Data Index: 1639422 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2349. Min Range: -5.2349
Max Act: 5.1724. Min Act: -0.1700
Data Index: 8719431 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2349. Min Range: -5.2349
Max Act: 5.1412. Min Act: -0.1700
Data Index: 4296872 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2349. Min Range: -5.2349
Max Act: 5.1724. Min Act: -0.1700
Data Index: 8432050 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2349. Min Range: -5.2349
Max Act: 5.1724. Min Act: -0.1700
Data Index: 2246575 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2349. Min Range: -5.2349
Max Act: 5.1724. Min Act: -0.1700
Data Index: 2562435 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2349. Min Range: -5.2349
Max Act: 5.1412. Min Act: -0.1700
Data Index: 470924 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2349. Min Range: -5.2349
Max Act: 5.1412. Min Act: -0.1700
Data Index: 8639522 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2349. Min Range: -5.2349
Max Act: 5.1099. Min Act: -0.1700
Data Index: 1610107 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2349. Min Range: -5.2349
Max Act: 5.1412. Min Act: -0.1700
Data Index: 6729983 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2349. Min Range: -5.2349
Max Act: 5.1099. Min Act: -0.1700
Data Index: 6391150 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2349. Min Range: -5.2349
Max Act: 5.1412. Min Act: -0.1700
Data Index: 2177083 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2349. Min Range: -5.2349
Max Act: 5.1412. Min Act: -0.1700
Data Index: 6002764 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2349. Min Range: -5.2349
Max Act: 5.1099. Min Act: -0.1700
Data Index: 2090563 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2349. Min Range: -5.2349
Max Act: 5.1412. Min Act: -0.1700
Data Index: 5852216 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2349. Min Range: -5.2349
Max Act: 5.1412. Min Act: -0.1700
Data Index: 537187 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2349. Min Range: -5.2349
Max Act: 5.1412. Min Act: -0.1700
Data Index: 5300327 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2349. Min Range: -5.2349
Max Act: 5.1099. Min Act: -0.1700
Data Index: 4648616 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2349. Min Range: -5.2349
Max Act: 5.1099. Min Act: -0.1700
Data Index: 4976073 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19