Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2010 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.7845. Min Range: -0.7845
Max Act: 0.7845. Min Act: -0.0001
Data Index: 616190 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7845. Min Range: -0.7845
Max Act: 0.6747. Min Act: -0.0001
Data Index: 40782 (C4 (Web Text))
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7845. Min Range: -0.7845
Max Act: 0.5933. Min Act: -0.0001
Data Index: 1354938 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7845. Min Range: -0.7845
Max Act: 0.6191. Min Act: -0.0001
Data Index: 1027530 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7845. Min Range: -0.7845
Max Act: 0.5541. Min Act: -0.0001
Data Index: 864790 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7845. Min Range: -0.7845
Max Act: 0.5801. Min Act: -0.0001
Data Index: 742813 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7845. Min Range: -0.7845
Max Act: 0.4866. Min Act: -0.0002
Data Index: 166365 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7845. Min Range: -0.7845
Max Act: 0.5011. Min Act: -0.0001
Data Index: 728571 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7845. Min Range: -0.7845
Max Act: 0.5072. Min Act: -0.0001
Data Index: 630458 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7845. Min Range: -0.7845
Max Act: 0.3693. Min Act: -0.0001
Data Index: 978138 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7845. Min Range: -0.7845
Max Act: 0.4948. Min Act: -0.0001
Data Index: 296126 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7845. Min Range: -0.7845
Max Act: 0.4879. Min Act: -0.0001
Data Index: 380809 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7845. Min Range: -0.7845
Max Act: 0.5030. Min Act: -0.0001
Data Index: 168411 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7845. Min Range: -0.7845
Max Act: 0.5026. Min Act: -0.0001
Data Index: 562390 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7845. Min Range: -0.7845
Max Act: 0.5232. Min Act: -0.0001
Data Index: 962666 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7845. Min Range: -0.7845
Max Act: 0.4817. Min Act: -0.0001
Data Index: 703995 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7845. Min Range: -0.7845
Max Act: 0.4990. Min Act: -0.0001
Data Index: 233464 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7845. Min Range: -0.7845
Max Act: 0.4773. Min Act: -0.0001
Data Index: 1286898 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7845. Min Range: -0.7845
Max Act: 0.4710. Min Act: -0.0001
Data Index: 76519 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7845. Min Range: -0.7845
Max Act: 0.4709. Min Act: -0.0001
Data Index: 333876 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19