Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3980 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.2824. Min Range: -2.2824
Max Act: 2.2824. Min Act: -0.0001
Data Index: 806011 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2824. Min Range: -2.2824
Max Act: 2.0787. Min Act: -0.0001
Data Index: 280025 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2824. Min Range: -2.2824
Max Act: 1.8783. Min Act: -0.0001
Data Index: 460469 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2824. Min Range: -2.2824
Max Act: 1.8948. Min Act: -0.0001
Data Index: 96626 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2824. Min Range: -2.2824
Max Act: 1.9906. Min Act: -0.0001
Data Index: 485635 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2824. Min Range: -2.2824
Max Act: 1.8560. Min Act: -0.0001
Data Index: 559529 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2824. Min Range: -2.2824
Max Act: 1.9304. Min Act: -0.0001
Data Index: 1403811 (Python Code)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2824. Min Range: -2.2824
Max Act: 1.8065. Min Act: -0.0001
Data Index: 760914 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2824. Min Range: -2.2824
Max Act: 1.8183. Min Act: -0.0001
Data Index: 139935 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2824. Min Range: -2.2824
Max Act: 1.8132. Min Act: -0.0001
Data Index: 743359 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2824. Min Range: -2.2824
Max Act: 1.7753. Min Act: -0.0001
Data Index: 897877 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2824. Min Range: -2.2824
Max Act: 1.7835. Min Act: -0.0001
Data Index: 646451 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2824. Min Range: -2.2824
Max Act: 1.7806. Min Act: -0.0001
Data Index: 642107 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2824. Min Range: -2.2824
Max Act: 1.4757. Min Act: -0.0001
Data Index: 140557 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2824. Min Range: -2.2824
Max Act: 1.6471. Min Act: -0.0001
Data Index: 476653 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2824. Min Range: -2.2824
Max Act: 1.8357. Min Act: -0.0001
Data Index: 368264 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2824. Min Range: -2.2824
Max Act: 1.6300. Min Act: -0.0001
Data Index: 598056 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2824. Min Range: -2.2824
Max Act: 1.7222. Min Act: -0.0001
Data Index: 949581 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2824. Min Range: -2.2824
Max Act: 1.8078. Min Act: -0.0001
Data Index: 985346 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2824. Min Range: -2.2824
Max Act: 1.6982. Min Act: -0.0001
Data Index: 656068 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19