Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1663 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.4536. Min Range: -2.4536
Max Act: 2.2461. Min Act: -0.0001
Data Index: 160612 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4536. Min Range: -2.4536
Max Act: 2.4536. Min Act: -0.0001
Data Index: 548007 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4536. Min Range: -2.4536
Max Act: 2.0779. Min Act: -0.0001
Data Index: 513439 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4536. Min Range: -2.4536
Max Act: 2.1041. Min Act: -0.0001
Data Index: 446671 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4536. Min Range: -2.4536
Max Act: 1.9700. Min Act: -0.0001
Data Index: 1245085 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4536. Min Range: -2.4536
Max Act: 2.0402. Min Act: -0.0001
Data Index: 883463 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4536. Min Range: -2.4536
Max Act: 1.9995. Min Act: -0.0001
Data Index: 961350 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4536. Min Range: -2.4536
Max Act: 1.8818. Min Act: -0.0001
Data Index: 992282 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4536. Min Range: -2.4536
Max Act: 1.8304. Min Act: -0.0001
Data Index: 638732 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4536. Min Range: -2.4536
Max Act: 1.9075. Min Act: -0.0001
Data Index: 638205 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4536. Min Range: -2.4536
Max Act: 1.8515. Min Act: -0.0001
Data Index: 700099 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4536. Min Range: -2.4536
Max Act: 1.8388. Min Act: -0.0001
Data Index: 583298 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4536. Min Range: -2.4536
Max Act: 1.9208. Min Act: -0.0001
Data Index: 286944 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4536. Min Range: -2.4536
Max Act: 1.7496. Min Act: -0.0001
Data Index: 699361 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4536. Min Range: -2.4536
Max Act: 1.9074. Min Act: -0.0001
Data Index: 781782 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4536. Min Range: -2.4536
Max Act: 1.6939. Min Act: -0.0001
Data Index: 165889 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4536. Min Range: -2.4536
Max Act: 1.8614. Min Act: -0.0001
Data Index: 976157 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4536. Min Range: -2.4536
Max Act: 1.8519. Min Act: -0.0001
Data Index: 559556 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4536. Min Range: -2.4536
Max Act: 1.8194. Min Act: -0.0001
Data Index: 1147146 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4536. Min Range: -2.4536
Max Act: 1.8521. Min Act: -0.0001
Data Index: 973321 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19