Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2669 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.5417. Min Range: -2.5417
Max Act: 2.5417. Min Act: -0.0001
Data Index: 3650 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5417. Min Range: -2.5417
Max Act: 2.5400. Min Act: -0.0001
Data Index: 467440 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5417. Min Range: -2.5417
Max Act: 2.4097. Min Act: -0.0001
Data Index: 995493 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5417. Min Range: -2.5417
Max Act: 2.4420. Min Act: -0.0001
Data Index: 915982 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5417. Min Range: -2.5417
Max Act: 2.2043. Min Act: -0.0001
Data Index: 240059 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5417. Min Range: -2.5417
Max Act: 2.2662. Min Act: -0.0001
Data Index: 339028 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5417. Min Range: -2.5417
Max Act: 1.9675. Min Act: -0.0001
Data Index: 771476 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5417. Min Range: -2.5417
Max Act: 2.1320. Min Act: -0.0001
Data Index: 910040 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5417. Min Range: -2.5417
Max Act: 2.2825. Min Act: -0.0001
Data Index: 1251945 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5417. Min Range: -2.5417
Max Act: 1.9952. Min Act: -0.0001
Data Index: 1260496 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5417. Min Range: -2.5417
Max Act: 2.1010. Min Act: -0.0001
Data Index: 295594 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5417. Min Range: -2.5417
Max Act: 2.2466. Min Act: -0.0001
Data Index: 406642 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5417. Min Range: -2.5417
Max Act: 1.9865. Min Act: -0.0001
Data Index: 1313587 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5417. Min Range: -2.5417
Max Act: 2.1171. Min Act: -0.0001
Data Index: 995362 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5417. Min Range: -2.5417
Max Act: 1.8601. Min Act: -0.0001
Data Index: 1682 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5417. Min Range: -2.5417
Max Act: 2.1276. Min Act: -0.0001
Data Index: 1016785 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5417. Min Range: -2.5417
Max Act: 2.0434. Min Act: -0.0001
Data Index: 413214 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5417. Min Range: -2.5417
Max Act: 2.0281. Min Act: -0.0001
Data Index: 1205709 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5417. Min Range: -2.5417
Max Act: 2.0505. Min Act: -0.0001
Data Index: 1129418 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5417. Min Range: -2.5417
Max Act: 2.0482. Min Act: -0.0001
Data Index: 1110390 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19