Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3423 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.9530. Min Range: -0.9530
Max Act: 0.9530. Min Act: -0.0001
Data Index: 875399 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9530. Min Range: -0.9530
Max Act: 0.8064. Min Act: -0.0001
Data Index: 1195640 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9530. Min Range: -0.9530
Max Act: 0.7958. Min Act: -0.0001
Data Index: 500227 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9530. Min Range: -0.9530
Max Act: 0.7411. Min Act: -0.0001
Data Index: 385239 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9530. Min Range: -0.9530
Max Act: 0.7299. Min Act: -0.0001
Data Index: 1255485 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9530. Min Range: -0.9530
Max Act: 0.8085. Min Act: -0.0001
Data Index: 704641 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9530. Min Range: -0.9530
Max Act: 0.6915. Min Act: -0.0001
Data Index: 1332330 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9530. Min Range: -0.9530
Max Act: 0.7865. Min Act: -0.0001
Data Index: 883103 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9530. Min Range: -0.9530
Max Act: 0.7521. Min Act: -0.0001
Data Index: 1076611 (C4 (Web Text))
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9530. Min Range: -0.9530
Max Act: 0.6749. Min Act: -0.0001
Data Index: 1359106 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9530. Min Range: -0.9530
Max Act: 0.6919. Min Act: -0.0001
Data Index: 1125171 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9530. Min Range: -0.9530
Max Act: 0.5789. Min Act: -0.0001
Data Index: 265133 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9530. Min Range: -0.9530
Max Act: 0.6366. Min Act: -0.0001
Data Index: 983854 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9530. Min Range: -0.9530
Max Act: 0.6263. Min Act: -0.0001
Data Index: 766532 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9530. Min Range: -0.9530
Max Act: 0.7054. Min Act: -0.0001
Data Index: 605282 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9530. Min Range: -0.9530
Max Act: 0.5944. Min Act: -0.0001
Data Index: 15546 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9530. Min Range: -0.9530
Max Act: 0.5723. Min Act: -0.0001
Data Index: 320354 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9530. Min Range: -0.9530
Max Act: 0.6141. Min Act: -0.0001
Data Index: 323283 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9530. Min Range: -0.9530
Max Act: 0.5398. Min Act: -0.0001
Data Index: 15288 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9530. Min Range: -0.9530
Max Act: 0.5954. Min Act: -0.0001
Data Index: 363041 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19