Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1042 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.9842. Min Range: -1.9842
Max Act: 1.9842. Min Act: -0.0001
Data Index: 126516 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9842. Min Range: -1.9842
Max Act: 1.8112. Min Act: -0.0001
Data Index: 291845 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9842. Min Range: -1.9842
Max Act: 1.7866. Min Act: -0.0001
Data Index: 1007496 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9842. Min Range: -1.9842
Max Act: 1.1468. Min Act: -0.0001
Data Index: 1531807 (The Pile)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9842. Min Range: -1.9842
Max Act: 1.5491. Min Act: -0.0001
Data Index: 1327704 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9842. Min Range: -1.9842
Max Act: 1.6278. Min Act: -0.0001
Data Index: 975999 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9842. Min Range: -1.9842
Max Act: 1.5242. Min Act: -0.0001
Data Index: 1067359 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9842. Min Range: -1.9842
Max Act: 1.5684. Min Act: -0.0001
Data Index: 1706567 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9842. Min Range: -1.9842
Max Act: 1.6408. Min Act: -0.0001
Data Index: 219832 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9842. Min Range: -1.9842
Max Act: 1.4888. Min Act: -0.0001
Data Index: 282 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9842. Min Range: -1.9842
Max Act: 1.4695. Min Act: -0.0001
Data Index: 169965 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9842. Min Range: -1.9842
Max Act: 1.5238. Min Act: -0.0001
Data Index: 161085 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9842. Min Range: -1.9842
Max Act: 1.3927. Min Act: -0.0001
Data Index: 79998 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9842. Min Range: -1.9842
Max Act: 1.4013. Min Act: -0.0001
Data Index: 1141431 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9842. Min Range: -1.9842
Max Act: 1.3692. Min Act: -0.0001
Data Index: 1941619 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9842. Min Range: -1.9842
Max Act: 1.5139. Min Act: -0.0001
Data Index: 1637685 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9842. Min Range: -1.9842
Max Act: 1.6981. Min Act: -0.0001
Data Index: 1127061 (The Pile)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9842. Min Range: -1.9842
Max Act: 1.4450. Min Act: -0.0001
Data Index: 580667 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9842. Min Range: -1.9842
Max Act: 1.4189. Min Act: -0.0001
Data Index: 135908 (The Pile)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9842. Min Range: -1.9842
Max Act: 1.3382. Min Act: -0.0001
Data Index: 1022582 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19