Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3399 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.2336. Min Range: -3.2336
Max Act: 3.2336. Min Act: -0.0001
Data Index: 430449 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2336. Min Range: -3.2336
Max Act: 3.1296. Min Act: -0.0001
Data Index: 921875 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2336. Min Range: -3.2336
Max Act: 2.9744. Min Act: -0.0001
Data Index: 916209 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2336. Min Range: -3.2336
Max Act: 2.8420. Min Act: -0.0001
Data Index: 790063 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2336. Min Range: -3.2336
Max Act: 2.7226. Min Act: -0.0001
Data Index: 553183 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2336. Min Range: -3.2336
Max Act: 2.5607. Min Act: -0.0001
Data Index: 230311 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2336. Min Range: -3.2336
Max Act: 2.6867. Min Act: -0.0001
Data Index: 677825 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2336. Min Range: -3.2336
Max Act: 2.4959. Min Act: -0.0001
Data Index: 1136718 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2336. Min Range: -3.2336
Max Act: 2.6585. Min Act: -0.0001
Data Index: 1043427 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2336. Min Range: -3.2336
Max Act: 2.5308. Min Act: -0.0001
Data Index: 1295928 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2336. Min Range: -3.2336
Max Act: 2.3977. Min Act: -0.0001
Data Index: 649699 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2336. Min Range: -3.2336
Max Act: 2.3688. Min Act: -0.0001
Data Index: 680268 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2336. Min Range: -3.2336
Max Act: 2.4658. Min Act: -0.0001
Data Index: 1086685 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2336. Min Range: -3.2336
Max Act: 2.3765. Min Act: -0.0001
Data Index: 1148076 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2336. Min Range: -3.2336
Max Act: 2.3634. Min Act: -0.0001
Data Index: 599074 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2336. Min Range: -3.2336
Max Act: 2.1091. Min Act: -0.0001
Data Index: 100623 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2336. Min Range: -3.2336
Max Act: 2.3453. Min Act: -0.0001
Data Index: 800685 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2336. Min Range: -3.2336
Max Act: 2.3078. Min Act: -0.0001
Data Index: 445520 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2336. Min Range: -3.2336
Max Act: 2.0536. Min Act: -0.0001
Data Index: 748145 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2336. Min Range: -3.2336
Max Act: 2.3608. Min Act: -0.0001
Data Index: 454210 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19