Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4037 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 3.1857. Min Range: -3.1857
Max Act: 3.1857. Min Act: -0.0001
Data Index: 1288448 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1857. Min Range: -3.1857
Max Act: 3.1528. Min Act: -0.0001
Data Index: 883133 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1857. Min Range: -3.1857
Max Act: 2.4915. Min Act: -0.0001
Data Index: 1079672 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1857. Min Range: -3.1857
Max Act: 2.4631. Min Act: -0.0001
Data Index: 1349165 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1857. Min Range: -3.1857
Max Act: 2.5890. Min Act: -0.0001
Data Index: 1010570 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1857. Min Range: -3.1857
Max Act: 2.4600. Min Act: -0.0001
Data Index: 342174 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1857. Min Range: -3.1857
Max Act: 2.3030. Min Act: -0.0001
Data Index: 1038856 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1857. Min Range: -3.1857
Max Act: 2.1630. Min Act: -0.0001
Data Index: 798343 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1857. Min Range: -3.1857
Max Act: 2.5142. Min Act: -0.0001
Data Index: 360086 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1857. Min Range: -3.1857
Max Act: 2.1597. Min Act: -0.0001
Data Index: 572657 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1857. Min Range: -3.1857
Max Act: 2.3826. Min Act: -0.0001
Data Index: 728562 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1857. Min Range: -3.1857
Max Act: 2.2329. Min Act: -0.0001
Data Index: 1147147 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1857. Min Range: -3.1857
Max Act: 2.2284. Min Act: -0.0001
Data Index: 811480 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1857. Min Range: -3.1857
Max Act: 2.0568. Min Act: -0.0001
Data Index: 41768 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1857. Min Range: -3.1857
Max Act: 2.2816. Min Act: -0.0001
Data Index: 231518 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1857. Min Range: -3.1857
Max Act: 2.2351. Min Act: -0.0001
Data Index: 695277 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1857. Min Range: -3.1857
Max Act: 2.0932. Min Act: -0.0001
Data Index: 850201 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1857. Min Range: -3.1857
Max Act: 2.0822. Min Act: -0.0001
Data Index: 1337026 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1857. Min Range: -3.1857
Max Act: 2.0857. Min Act: -0.0001
Data Index: 1321924 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1857. Min Range: -3.1857
Max Act: 1.8849. Min Act: -0.0001
Data Index: 151137 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19