Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4334 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.9404. Min Range: -2.9404
Max Act: 2.9404. Min Act: -0.0001
Data Index: 5441 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9404. Min Range: -2.9404
Max Act: 2.6138. Min Act: -0.0001
Data Index: 981906 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9404. Min Range: -2.9404
Max Act: 2.5013. Min Act: -0.0001
Data Index: 1191362 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9404. Min Range: -2.9404
Max Act: 2.5850. Min Act: -0.0001
Data Index: 1163520 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9404. Min Range: -2.9404
Max Act: 2.5722. Min Act: -0.0001
Data Index: 682899 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9404. Min Range: -2.9404
Max Act: 2.5656. Min Act: -0.0001
Data Index: 406797 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9404. Min Range: -2.9404
Max Act: 2.7661. Min Act: -0.0001
Data Index: 1346870 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9404. Min Range: -2.9404
Max Act: 2.4827. Min Act: -0.0001
Data Index: 422101 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9404. Min Range: -2.9404
Max Act: 2.4635. Min Act: -0.0001
Data Index: 922585 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9404. Min Range: -2.9404
Max Act: 2.3228. Min Act: -0.0001
Data Index: 903635 (C4 (Web Text))
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9404. Min Range: -2.9404
Max Act: 2.2978. Min Act: -0.0001
Data Index: 1207364 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9404. Min Range: -2.9404
Max Act: 2.4458. Min Act: -0.0001
Data Index: 1075722 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9404. Min Range: -2.9404
Max Act: 2.2911. Min Act: -0.0001
Data Index: 609714 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9404. Min Range: -2.9404
Max Act: 2.6404. Min Act: -0.0001
Data Index: 1132431 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9404. Min Range: -2.9404
Max Act: 2.5035. Min Act: -0.0001
Data Index: 1273104 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9404. Min Range: -2.9404
Max Act: 2.4858. Min Act: -0.0001
Data Index: 1227483 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9404. Min Range: -2.9404
Max Act: 2.2251. Min Act: -0.0001
Data Index: 659918 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9404. Min Range: -2.9404
Max Act: 2.4521. Min Act: -0.0001
Data Index: 139000 (C4 (Web Text))
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9404. Min Range: -2.9404
Max Act: 2.4369. Min Act: -0.0001
Data Index: 386620 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9404. Min Range: -2.9404
Max Act: 2.2982. Min Act: -0.0001
Data Index: 1264851 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19