Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2506 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.2982. Min Range: -3.2982
Max Act: 3.2982. Min Act: -0.0001
Data Index: 1046125 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2982. Min Range: -3.2982
Max Act: 3.1412. Min Act: -0.0001
Data Index: 379243 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2982. Min Range: -3.2982
Max Act: 3.0454. Min Act: -0.0001
Data Index: 628153 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2982. Min Range: -3.2982
Max Act: 3.0061. Min Act: -0.0001
Data Index: 1089346 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2982. Min Range: -3.2982
Max Act: 3.2685. Min Act: -0.0001
Data Index: 251987 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2982. Min Range: -3.2982
Max Act: 2.9292. Min Act: -0.0001
Data Index: 1241532 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2982. Min Range: -3.2982
Max Act: 2.9068. Min Act: -0.0001
Data Index: 255052 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2982. Min Range: -3.2982
Max Act: 3.1341. Min Act: -0.0001
Data Index: 925828 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2982. Min Range: -3.2982
Max Act: 2.6925. Min Act: -0.0001
Data Index: 786577 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2982. Min Range: -3.2982
Max Act: 2.8024. Min Act: -0.0001
Data Index: 1101809 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2982. Min Range: -3.2982
Max Act: 2.6522. Min Act: -0.0001
Data Index: 135468 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2982. Min Range: -3.2982
Max Act: 2.8524. Min Act: -0.0001
Data Index: 593258 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2982. Min Range: -3.2982
Max Act: 2.5584. Min Act: -0.0001
Data Index: 1234478 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2982. Min Range: -3.2982
Max Act: 2.7445. Min Act: -0.0001
Data Index: 137913 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2982. Min Range: -3.2982
Max Act: 2.5716. Min Act: -0.0001
Data Index: 1066880 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2982. Min Range: -3.2982
Max Act: 2.8528. Min Act: -0.0001
Data Index: 1079799 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2982. Min Range: -3.2982
Max Act: 2.4315. Min Act: -0.0001
Data Index: 176267 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2982. Min Range: -3.2982
Max Act: 2.5178. Min Act: -0.0001
Data Index: 883358 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2982. Min Range: -3.2982
Max Act: 2.5028. Min Act: -0.0001
Data Index: 1033890 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2982. Min Range: -3.2982
Max Act: 2.7866. Min Act: -0.0001
Data Index: 889109 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19