Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2905 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 4.9639. Min Range: -4.9639
Max Act: 4.9639. Min Act: -0.0001
Data Index: 531482 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9639. Min Range: -4.9639
Max Act: 4.9218. Min Act: -0.0001
Data Index: 49738 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9639. Min Range: -4.9639
Max Act: 4.2864. Min Act: -0.0001
Data Index: 1142307 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9639. Min Range: -4.9639
Max Act: 4.3168. Min Act: -0.0000
Data Index: 1065604 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9639. Min Range: -4.9639
Max Act: 4.5681. Min Act: -0.0001
Data Index: 1158103 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9639. Min Range: -4.9639
Max Act: 4.1306. Min Act: -0.0001
Data Index: 31814 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9639. Min Range: -4.9639
Max Act: 4.0832. Min Act: -0.0001
Data Index: 30845 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9639. Min Range: -4.9639
Max Act: 4.0600. Min Act: -0.0001
Data Index: 788783 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9639. Min Range: -4.9639
Max Act: 3.8817. Min Act: -0.0001
Data Index: 600237 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9639. Min Range: -4.9639
Max Act: 4.0052. Min Act: -0.0001
Data Index: 418721 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9639. Min Range: -4.9639
Max Act: 3.8414. Min Act: -0.0001
Data Index: 1165564 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9639. Min Range: -4.9639
Max Act: 3.9145. Min Act: -0.0001
Data Index: 285868 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9639. Min Range: -4.9639
Max Act: 3.9087. Min Act: -0.0001
Data Index: 1054862 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9639. Min Range: -4.9639
Max Act: 4.0451. Min Act: -0.0001
Data Index: 634559 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9639. Min Range: -4.9639
Max Act: 3.6750. Min Act: -0.0001
Data Index: 980901 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9639. Min Range: -4.9639
Max Act: 3.4064. Min Act: -0.0001
Data Index: 1163518 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9639. Min Range: -4.9639
Max Act: 3.9713. Min Act: -0.0001
Data Index: 847029 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9639. Min Range: -4.9639
Max Act: 3.6679. Min Act: -0.0001
Data Index: 1176013 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9639. Min Range: -4.9639
Max Act: 3.8255. Min Act: -0.0001
Data Index: 848399 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9639. Min Range: -4.9639
Max Act: 3.5579. Min Act: -0.0001
Data Index: 483604 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19