Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3640 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.6863. Min Range: -2.6863
Max Act: 2.6863. Min Act: -0.0001
Data Index: 425336 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6863. Min Range: -2.6863
Max Act: 2.4325. Min Act: -0.0001
Data Index: 1015829 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6863. Min Range: -2.6863
Max Act: 2.3977. Min Act: -0.0001
Data Index: 1288681 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6863. Min Range: -2.6863
Max Act: 2.2568. Min Act: -0.0001
Data Index: 881626 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6863. Min Range: -2.6863
Max Act: 2.2193. Min Act: -0.0001
Data Index: 397968 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6863. Min Range: -2.6863
Max Act: 2.1758. Min Act: -0.0001
Data Index: 1232443 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6863. Min Range: -2.6863
Max Act: 1.8493. Min Act: -0.0001
Data Index: 130427 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6863. Min Range: -2.6863
Max Act: 2.1453. Min Act: -0.0001
Data Index: 626705 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6863. Min Range: -2.6863
Max Act: 2.1421. Min Act: -0.0001
Data Index: 1080026 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6863. Min Range: -2.6863
Max Act: 2.0192. Min Act: -0.0001
Data Index: 1240085 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6863. Min Range: -2.6863
Max Act: 1.9900. Min Act: -0.0001
Data Index: 813526 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6863. Min Range: -2.6863
Max Act: 1.9099. Min Act: -0.0001
Data Index: 479526 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6863. Min Range: -2.6863
Max Act: 1.9078. Min Act: -0.0001
Data Index: 573394 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6863. Min Range: -2.6863
Max Act: 1.9046. Min Act: -0.0001
Data Index: 1269416 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6863. Min Range: -2.6863
Max Act: 1.8754. Min Act: -0.0001
Data Index: 1008599 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6863. Min Range: -2.6863
Max Act: 1.8735. Min Act: -0.0001
Data Index: 122867 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6863. Min Range: -2.6863
Max Act: 1.7757. Min Act: -0.0001
Data Index: 743380 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6863. Min Range: -2.6863
Max Act: 1.8816. Min Act: -0.0001
Data Index: 296661 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6863. Min Range: -2.6863
Max Act: 1.8458. Min Act: -0.0001
Data Index: 1083881 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6863. Min Range: -2.6863
Max Act: 1.9465. Min Act: -0.0001
Data Index: 1189187 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19