Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1008 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.0439. Min Range: -0.0439
Max Act: 0.0439. Min Act: 0.0000
Data Index: 15197 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0439. Min Range: -0.0439
Max Act: 0.0439. Min Act: 0.0000
Data Index: 337632 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0439. Min Range: -0.0439
Max Act: 0.0439. Min Act: 0.0000
Data Index: 452992 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0439. Min Range: -0.0439
Max Act: 0.0439. Min Act: 0.0000
Data Index: 559016 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0439. Min Range: -0.0439
Max Act: 0.0439. Min Act: 0.0000
Data Index: 582247 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0439. Min Range: -0.0439
Max Act: 0.0439. Min Act: 0.0000
Data Index: 513644 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0439. Min Range: -0.0439
Max Act: 0.0439. Min Act: 0.0000
Data Index: 8318 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0439. Min Range: -0.0439
Max Act: 0.0439. Min Act: 0.0000
Data Index: 114933 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0439. Min Range: -0.0439
Max Act: 0.0439. Min Act: 0.0000
Data Index: 77369 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0439. Min Range: -0.0439
Max Act: 0.0439. Min Act: 0.0001
Data Index: 583733 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0439. Min Range: -0.0439
Max Act: 0.0439. Min Act: 0.0000
Data Index: 254100 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0439. Min Range: -0.0439
Max Act: 0.0439. Min Act: 0.0000
Data Index: 724070 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0439. Min Range: -0.0439
Max Act: 0.0439. Min Act: 0.0000
Data Index: 704009 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0439. Min Range: -0.0439
Max Act: 0.0439. Min Act: 0.0000
Data Index: 346937 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0439. Min Range: -0.0439
Max Act: 0.0439. Min Act: 0.0000
Data Index: 414487 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0439. Min Range: -0.0439
Max Act: 0.0439. Min Act: 0.0000
Data Index: 269144 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0439. Min Range: -0.0439
Max Act: 0.0439. Min Act: 0.0000
Data Index: 194919 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0439. Min Range: -0.0439
Max Act: 0.0439. Min Act: -0.0000
Data Index: 93103 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0439. Min Range: -0.0439
Max Act: 0.0439. Min Act: 0.0000
Data Index: 512011 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0439. Min Range: -0.0439
Max Act: 0.0439. Min Act: -0.0000
Data Index: 97399 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19