Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 44 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.0210. Min Range: -2.0210
Max Act: 2.0210. Min Act: -0.0001
Data Index: 1113696 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0210. Min Range: -2.0210
Max Act: 1.2294. Min Act: -0.0001
Data Index: 488524 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0210. Min Range: -2.0210
Max Act: 1.3635. Min Act: -0.0001
Data Index: 139448 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0210. Min Range: -2.0210
Max Act: 1.3009. Min Act: -0.0001
Data Index: 188038 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0210. Min Range: -2.0210
Max Act: 1.3641. Min Act: -0.0001
Data Index: 362748 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0210. Min Range: -2.0210
Max Act: 1.2065. Min Act: -0.0001
Data Index: 784831 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0210. Min Range: -2.0210
Max Act: 1.3330. Min Act: -0.0001
Data Index: 143148 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0210. Min Range: -2.0210
Max Act: 1.2350. Min Act: -0.0001
Data Index: 1255638 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0210. Min Range: -2.0210
Max Act: 1.1601. Min Act: -0.0001
Data Index: 542109 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0210. Min Range: -2.0210
Max Act: 1.2504. Min Act: -0.0001
Data Index: 1154775 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0210. Min Range: -2.0210
Max Act: 1.2440. Min Act: -0.0001
Data Index: 57830 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0210. Min Range: -2.0210
Max Act: 1.3199. Min Act: -0.0001
Data Index: 513862 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0210. Min Range: -2.0210
Max Act: 1.2477. Min Act: -0.0001
Data Index: 188147 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0210. Min Range: -2.0210
Max Act: 1.3065. Min Act: -0.0001
Data Index: 82994 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0210. Min Range: -2.0210
Max Act: 1.3823. Min Act: -0.0001
Data Index: 343013 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0210. Min Range: -2.0210
Max Act: 1.2233. Min Act: -0.0001
Data Index: 1236034 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0210. Min Range: -2.0210
Max Act: 1.2094. Min Act: -0.0001
Data Index: 441544 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0210. Min Range: -2.0210
Max Act: 1.0035. Min Act: -0.0001
Data Index: 845554 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0210. Min Range: -2.0210
Max Act: 1.0805. Min Act: -0.0001
Data Index: 901422 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0210. Min Range: -2.0210
Max Act: 1.0870. Min Act: -0.0001
Data Index: 1319543 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19