Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4390 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.8669. Min Range: -1.8669
Max Act: 1.7615. Min Act: -0.0001
Data Index: 522103 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8669. Min Range: -1.8669
Max Act: 1.8669. Min Act: -0.0001
Data Index: 904560 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8669. Min Range: -1.8669
Max Act: 1.7613. Min Act: -0.0001
Data Index: 1006650 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8669. Min Range: -1.8669
Max Act: 1.5421. Min Act: -0.0001
Data Index: 1151404 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8669. Min Range: -1.8669
Max Act: 1.6983. Min Act: -0.0001
Data Index: 431543 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8669. Min Range: -1.8669
Max Act: 1.4744. Min Act: -0.0001
Data Index: 48476 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8669. Min Range: -1.8669
Max Act: 1.5552. Min Act: -0.0001
Data Index: 99349 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8669. Min Range: -1.8669
Max Act: 1.5645. Min Act: -0.0001
Data Index: 967954 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8669. Min Range: -1.8669
Max Act: 1.5196. Min Act: -0.0001
Data Index: 96672 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8669. Min Range: -1.8669
Max Act: 1.4674. Min Act: -0.0001
Data Index: 267506 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8669. Min Range: -1.8669
Max Act: 1.5655. Min Act: -0.0001
Data Index: 948703 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8669. Min Range: -1.8669
Max Act: 1.6575. Min Act: -0.0001
Data Index: 989670 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8669. Min Range: -1.8669
Max Act: 1.4420. Min Act: -0.0001
Data Index: 156830 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8669. Min Range: -1.8669
Max Act: 1.4017. Min Act: -0.0001
Data Index: 1144495 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8669. Min Range: -1.8669
Max Act: 1.2840. Min Act: -0.0001
Data Index: 498160 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8669. Min Range: -1.8669
Max Act: 1.4343. Min Act: -0.0001
Data Index: 60913 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8669. Min Range: -1.8669
Max Act: 1.4929. Min Act: -0.0001
Data Index: 38635 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8669. Min Range: -1.8669
Max Act: 1.3117. Min Act: -0.0001
Data Index: 665357 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8669. Min Range: -1.8669
Max Act: 1.3292. Min Act: -0.0001
Data Index: 823830 (C4 (Web Text))
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8669. Min Range: -1.8669
Max Act: 1.3855. Min Act: -0.0001
Data Index: 312108 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19