Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2846 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.2802. Min Range: -2.2802
Max Act: 2.2802. Min Act: -0.0001
Data Index: 1068297 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2802. Min Range: -2.2802
Max Act: 2.2511. Min Act: -0.0001
Data Index: 533997 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2802. Min Range: -2.2802
Max Act: 2.1652. Min Act: -0.0001
Data Index: 84375 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2802. Min Range: -2.2802
Max Act: 2.2421. Min Act: -0.0001
Data Index: 644681 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2802. Min Range: -2.2802
Max Act: 2.1892. Min Act: -0.0001
Data Index: 872920 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2802. Min Range: -2.2802
Max Act: 2.1050. Min Act: -0.0001
Data Index: 705910 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2802. Min Range: -2.2802
Max Act: 1.9961. Min Act: -0.0001
Data Index: 835761 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2802. Min Range: -2.2802
Max Act: 2.0370. Min Act: -0.0001
Data Index: 548520 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2802. Min Range: -2.2802
Max Act: 2.0132. Min Act: -0.0001
Data Index: 1245513 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2802. Min Range: -2.2802
Max Act: 1.9169. Min Act: -0.0001
Data Index: 1166231 (C4 (Web Text))
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2802. Min Range: -2.2802
Max Act: 1.9045. Min Act: -0.0001
Data Index: 1286112 (C4 (Web Text))
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2802. Min Range: -2.2802
Max Act: 1.8045. Min Act: -0.0001
Data Index: 645084 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2802. Min Range: -2.2802
Max Act: 2.0777. Min Act: -0.0001
Data Index: 1307446 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2802. Min Range: -2.2802
Max Act: 1.8696. Min Act: -0.0001
Data Index: 1224510 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2802. Min Range: -2.2802
Max Act: 1.8741. Min Act: -0.0001
Data Index: 433434 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2802. Min Range: -2.2802
Max Act: 1.9432. Min Act: -0.0001
Data Index: 999044 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2802. Min Range: -2.2802
Max Act: 1.9434. Min Act: -0.0001
Data Index: 1290858 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2802. Min Range: -2.2802
Max Act: 1.7531. Min Act: -0.0001
Data Index: 709930 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2802. Min Range: -2.2802
Max Act: 1.8377. Min Act: -0.0001
Data Index: 1258930 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2802. Min Range: -2.2802
Max Act: 1.9104. Min Act: -0.0001
Data Index: 1273237 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19