Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3807 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.2645. Min Range: -3.2645
Max Act: 3.2645. Min Act: -0.0001
Data Index: 842625 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2645. Min Range: -3.2645
Max Act: 3.1400. Min Act: -0.0001
Data Index: 1257570 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2645. Min Range: -3.2645
Max Act: 2.7178. Min Act: -0.0001
Data Index: 458015 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2645. Min Range: -3.2645
Max Act: 2.6193. Min Act: -0.0001
Data Index: 1220589 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2645. Min Range: -3.2645
Max Act: 2.4608. Min Act: -0.0001
Data Index: 1179253 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2645. Min Range: -3.2645
Max Act: 2.7447. Min Act: -0.0001
Data Index: 696348 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2645. Min Range: -3.2645
Max Act: 2.7038. Min Act: -0.0001
Data Index: 304945 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2645. Min Range: -3.2645
Max Act: 2.2587. Min Act: -0.0001
Data Index: 764884 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2645. Min Range: -3.2645
Max Act: 2.7122. Min Act: -0.0001
Data Index: 1101681 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2645. Min Range: -3.2645
Max Act: 2.2826. Min Act: -0.0001
Data Index: 1478139 (Python Code)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2645. Min Range: -3.2645
Max Act: 2.2935. Min Act: -0.0001
Data Index: 207466 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2645. Min Range: -3.2645
Max Act: 2.3636. Min Act: -0.0001
Data Index: 806072 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2645. Min Range: -3.2645
Max Act: 1.8771. Min Act: -0.0001
Data Index: 1292941 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2645. Min Range: -3.2645
Max Act: 2.1208. Min Act: -0.0001
Data Index: 1018004 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2645. Min Range: -3.2645
Max Act: 1.9357. Min Act: -0.0001
Data Index: 1400826 (Python Code)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2645. Min Range: -3.2645
Max Act: 2.1412. Min Act: -0.0001
Data Index: 41558 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2645. Min Range: -3.2645
Max Act: 2.0098. Min Act: -0.0001
Data Index: 1190196 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2645. Min Range: -3.2645
Max Act: 2.0995. Min Act: -0.0001
Data Index: 465597 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2645. Min Range: -3.2645
Max Act: 2.1253. Min Act: -0.0001
Data Index: 1059139 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2645. Min Range: -3.2645
Max Act: 1.9271. Min Act: -0.0001
Data Index: 303355 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19