Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2762 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.5422. Min Range: -1.5422
Max Act: 1.5422. Min Act: -0.0001
Data Index: 1279610 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5422. Min Range: -1.5422
Max Act: 1.4417. Min Act: -0.0001
Data Index: 861323 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5422. Min Range: -1.5422
Max Act: 1.3715. Min Act: -0.0001
Data Index: 1401345 (Python Code)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5422. Min Range: -1.5422
Max Act: 1.3047. Min Act: -0.0001
Data Index: 259602 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5422. Min Range: -1.5422
Max Act: 1.2952. Min Act: -0.0001
Data Index: 1162630 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5422. Min Range: -1.5422
Max Act: 1.3080. Min Act: -0.0001
Data Index: 979558 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5422. Min Range: -1.5422
Max Act: 1.3004. Min Act: -0.0001
Data Index: 1280754 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5422. Min Range: -1.5422
Max Act: 1.1447. Min Act: -0.0001
Data Index: 509706 (C4 (Web Text))
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5422. Min Range: -1.5422
Max Act: 1.2477. Min Act: -0.0001
Data Index: 163738 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5422. Min Range: -1.5422
Max Act: 1.2271. Min Act: -0.0001
Data Index: 150739 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5422. Min Range: -1.5422
Max Act: 1.2621. Min Act: -0.0001
Data Index: 1469829 (Python Code)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5422. Min Range: -1.5422
Max Act: 1.1766. Min Act: -0.0001
Data Index: 1195271 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5422. Min Range: -1.5422
Max Act: 1.2832. Min Act: -0.0001
Data Index: 668105 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5422. Min Range: -1.5422
Max Act: 1.1779. Min Act: -0.0001
Data Index: 369860 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5422. Min Range: -1.5422
Max Act: 1.2247. Min Act: -0.0001
Data Index: 949782 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5422. Min Range: -1.5422
Max Act: 1.1595. Min Act: -0.0001
Data Index: 745579 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5422. Min Range: -1.5422
Max Act: 1.2517. Min Act: -0.0001
Data Index: 424449 (C4 (Web Text))
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5422. Min Range: -1.5422
Max Act: 1.1434. Min Act: -0.0001
Data Index: 1031117 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5422. Min Range: -1.5422
Max Act: 1.1276. Min Act: -0.0001
Data Index: 1320805 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5422. Min Range: -1.5422
Max Act: 1.0728. Min Act: -0.0001
Data Index: 994771 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19