Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3281 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.1280. Min Range: -1.1280
Max Act: 1.1280. Min Act: -0.0001
Data Index: 236586 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1280. Min Range: -1.1280
Max Act: 1.0493. Min Act: -0.0001
Data Index: 235485 (C4 (Web Text))
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1280. Min Range: -1.1280
Max Act: 0.9994. Min Act: -0.0001
Data Index: 1627347 (Python Code)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1280. Min Range: -1.1280
Max Act: 1.0390. Min Act: -0.0001
Data Index: 914113 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1280. Min Range: -1.1280
Max Act: 0.9165. Min Act: -0.0001
Data Index: 1210924 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1280. Min Range: -1.1280
Max Act: 0.8510. Min Act: -0.0001
Data Index: 464221 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1280. Min Range: -1.1280
Max Act: 0.9174. Min Act: -0.0001
Data Index: 365708 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1280. Min Range: -1.1280
Max Act: 0.8075. Min Act: -0.0001
Data Index: 1225484 (C4 (Web Text))
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1280. Min Range: -1.1280
Max Act: 0.8248. Min Act: -0.0001
Data Index: 776945 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1280. Min Range: -1.1280
Max Act: 0.8413. Min Act: -0.0001
Data Index: 332513 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1280. Min Range: -1.1280
Max Act: 0.8132. Min Act: -0.0001
Data Index: 1290244 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1280. Min Range: -1.1280
Max Act: 0.7786. Min Act: -0.0001
Data Index: 596540 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1280. Min Range: -1.1280
Max Act: 0.7727. Min Act: -0.0001
Data Index: 516343 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1280. Min Range: -1.1280
Max Act: 0.7498. Min Act: -0.0001
Data Index: 855878 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1280. Min Range: -1.1280
Max Act: 0.7661. Min Act: -0.0001
Data Index: 1273507 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1280. Min Range: -1.1280
Max Act: 0.7308. Min Act: -0.0001
Data Index: 642153 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1280. Min Range: -1.1280
Max Act: 0.7396. Min Act: -0.0001
Data Index: 1427492 (Python Code)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1280. Min Range: -1.1280
Max Act: 0.7657. Min Act: -0.0001
Data Index: 87333 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1280. Min Range: -1.1280
Max Act: 0.8060. Min Act: -0.0001
Data Index: 1065270 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1280. Min Range: -1.1280
Max Act: 0.7533. Min Act: -0.0001
Data Index: 584250 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19