Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2843 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.8763. Min Range: -3.8763
Max Act: 3.6378. Min Act: -0.0001
Data Index: 1075129 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8763. Min Range: -3.8763
Max Act: 3.7187. Min Act: -0.0001
Data Index: 156057 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8763. Min Range: -3.8763
Max Act: 3.8763. Min Act: -0.0001
Data Index: 870068 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8763. Min Range: -3.8763
Max Act: 3.6044. Min Act: -0.0001
Data Index: 157527 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8763. Min Range: -3.8763
Max Act: 3.1989. Min Act: -0.0001
Data Index: 855115 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8763. Min Range: -3.8763
Max Act: 2.9064. Min Act: -0.0001
Data Index: 1285506 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8763. Min Range: -3.8763
Max Act: 2.6763. Min Act: -0.0001
Data Index: 792983 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8763. Min Range: -3.8763
Max Act: 2.3317. Min Act: -0.0001
Data Index: 113694 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8763. Min Range: -3.8763
Max Act: 2.3019. Min Act: -0.0001
Data Index: 334722 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8763. Min Range: -3.8763
Max Act: 2.4320. Min Act: -0.0001
Data Index: 1236556 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8763. Min Range: -3.8763
Max Act: 2.4395. Min Act: -0.0001
Data Index: 94980 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8763. Min Range: -3.8763
Max Act: 2.3988. Min Act: -0.0001
Data Index: 821759 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8763. Min Range: -3.8763
Max Act: 2.4973. Min Act: -0.0001
Data Index: 686726 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8763. Min Range: -3.8763
Max Act: 2.3789. Min Act: -0.0001
Data Index: 115702 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8763. Min Range: -3.8763
Max Act: 2.3794. Min Act: -0.0001
Data Index: 307435 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8763. Min Range: -3.8763
Max Act: 2.1144. Min Act: -0.0001
Data Index: 806186 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8763. Min Range: -3.8763
Max Act: 2.3455. Min Act: -0.0001
Data Index: 33600 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8763. Min Range: -3.8763
Max Act: 2.0699. Min Act: -0.0001
Data Index: 1218650 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8763. Min Range: -3.8763
Max Act: 2.2682. Min Act: -0.0001
Data Index: 181864 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8763. Min Range: -3.8763
Max Act: 2.3672. Min Act: -0.0001
Data Index: 110464 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19