Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4309 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.6077. Min Range: -3.6077
Max Act: 3.5471. Min Act: -0.0001
Data Index: 994792 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6077. Min Range: -3.6077
Max Act: 3.6077. Min Act: -0.0001
Data Index: 1019681 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6077. Min Range: -3.6077
Max Act: 3.0731. Min Act: -0.0001
Data Index: 23614 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6077. Min Range: -3.6077
Max Act: 2.9802. Min Act: -0.0001
Data Index: 1357888 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6077. Min Range: -3.6077
Max Act: 2.7801. Min Act: -0.0001
Data Index: 903461 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6077. Min Range: -3.6077
Max Act: 2.5763. Min Act: -0.0001
Data Index: 616494 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6077. Min Range: -3.6077
Max Act: 2.6915. Min Act: -0.0001
Data Index: 510112 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6077. Min Range: -3.6077
Max Act: 2.6101. Min Act: -0.0001
Data Index: 732318 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6077. Min Range: -3.6077
Max Act: 2.4670. Min Act: -0.0001
Data Index: 670376 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6077. Min Range: -3.6077
Max Act: 2.6219. Min Act: -0.0001
Data Index: 489172 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6077. Min Range: -3.6077
Max Act: 2.5879. Min Act: -0.0001
Data Index: 1155892 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6077. Min Range: -3.6077
Max Act: 2.4621. Min Act: -0.0001
Data Index: 1163267 (C4 (Web Text))
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6077. Min Range: -3.6077
Max Act: 2.5794. Min Act: -0.0001
Data Index: 26435 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6077. Min Range: -3.6077
Max Act: 2.4401. Min Act: -0.0001
Data Index: 390381 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6077. Min Range: -3.6077
Max Act: 2.4002. Min Act: -0.0001
Data Index: 501910 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6077. Min Range: -3.6077
Max Act: 2.4143. Min Act: -0.0001
Data Index: 994886 (C4 (Web Text))
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6077. Min Range: -3.6077
Max Act: 2.6506. Min Act: -0.0001
Data Index: 158570 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6077. Min Range: -3.6077
Max Act: 2.3540. Min Act: -0.0001
Data Index: 187315 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6077. Min Range: -3.6077
Max Act: 2.4645. Min Act: -0.0001
Data Index: 364276 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6077. Min Range: -3.6077
Max Act: 2.4675. Min Act: -0.0001
Data Index: 1124818 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19