Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5177 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.1681. Min Range: -2.1681
Max Act: 2.1681. Min Act: -0.0000
Data Index: 772947 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1681. Min Range: -2.1681
Max Act: 2.0517. Min Act: -0.0001
Data Index: 1305571 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1681. Min Range: -2.1681
Max Act: 1.9930. Min Act: -0.0001
Data Index: 1039103 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1681. Min Range: -2.1681
Max Act: 1.7784. Min Act: -0.0000
Data Index: 88888 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1681. Min Range: -2.1681
Max Act: 1.4745. Min Act: -0.0001
Data Index: 364522 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1681. Min Range: -2.1681
Max Act: 1.6619. Min Act: -0.0000
Data Index: 620095 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1681. Min Range: -2.1681
Max Act: 1.7058. Min Act: -0.0000
Data Index: 707242 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1681. Min Range: -2.1681
Max Act: 1.6622. Min Act: -0.0001
Data Index: 1178971 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1681. Min Range: -2.1681
Max Act: 1.4882. Min Act: -0.0001
Data Index: 595077 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1681. Min Range: -2.1681
Max Act: 1.3746. Min Act: -0.0001
Data Index: 133263 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1681. Min Range: -2.1681
Max Act: 1.3620. Min Act: -0.0001
Data Index: 237125 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1681. Min Range: -2.1681
Max Act: 1.3591. Min Act: -0.0001
Data Index: 1599172 (Python Code)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1681. Min Range: -2.1681
Max Act: 1.3311. Min Act: -0.0001
Data Index: 1224566 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1681. Min Range: -2.1681
Max Act: 1.3172. Min Act: -0.0000
Data Index: 378332 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1681. Min Range: -2.1681
Max Act: 1.4031. Min Act: -0.0001
Data Index: 24732 (C4 (Web Text))
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1681. Min Range: -2.1681
Max Act: 1.2634. Min Act: -0.0001
Data Index: 570331 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1681. Min Range: -2.1681
Max Act: 1.2575. Min Act: -0.0001
Data Index: 1393896 (Python Code)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1681. Min Range: -2.1681
Max Act: 1.1169. Min Act: -0.0001
Data Index: 1115695 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1681. Min Range: -2.1681
Max Act: 1.2413. Min Act: -0.0000
Data Index: 66581 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1681. Min Range: -2.1681
Max Act: 1.2590. Min Act: -0.0001
Data Index: 221611 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19