Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2983 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.0225. Min Range: -1.0225
Max Act: 1.0225. Min Act: -0.0001
Data Index: 1345570 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0225. Min Range: -1.0225
Max Act: 0.9709. Min Act: -0.0001
Data Index: 168327 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0225. Min Range: -1.0225
Max Act: 1.0043. Min Act: -0.0001
Data Index: 908663 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0225. Min Range: -1.0225
Max Act: 0.9829. Min Act: -0.0001
Data Index: 1002993 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0225. Min Range: -1.0225
Max Act: 0.9892. Min Act: -0.0001
Data Index: 550019 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0225. Min Range: -1.0225
Max Act: 0.9847. Min Act: -0.0001
Data Index: 1276036 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0225. Min Range: -1.0225
Max Act: 0.9352. Min Act: -0.0001
Data Index: 515454 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0225. Min Range: -1.0225
Max Act: 1.0074. Min Act: -0.0001
Data Index: 153294 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0225. Min Range: -1.0225
Max Act: 0.9980. Min Act: -0.0001
Data Index: 323574 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0225. Min Range: -1.0225
Max Act: 0.9790. Min Act: -0.0001
Data Index: 277428 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0225. Min Range: -1.0225
Max Act: 0.9717. Min Act: -0.0001
Data Index: 1328758 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0225. Min Range: -1.0225
Max Act: 0.9602. Min Act: -0.0001
Data Index: 374737 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0225. Min Range: -1.0225
Max Act: 0.9650. Min Act: -0.0001
Data Index: 1266632 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0225. Min Range: -1.0225
Max Act: 0.9859. Min Act: -0.0001
Data Index: 411489 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0225. Min Range: -1.0225
Max Act: 0.9488. Min Act: -0.0001
Data Index: 966397 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0225. Min Range: -1.0225
Max Act: 1.0052. Min Act: -0.0001
Data Index: 286861 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0225. Min Range: -1.0225
Max Act: 0.9444. Min Act: -0.0001
Data Index: 456187 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0225. Min Range: -1.0225
Max Act: 0.9167. Min Act: -0.0001
Data Index: 445993 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0225. Min Range: -1.0225
Max Act: 0.9287. Min Act: -0.0001
Data Index: 701493 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0225. Min Range: -1.0225
Max Act: 0.9045. Min Act: -0.0001
Data Index: 785328 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19