Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 6087 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.4651. Min Range: -2.4651
Max Act: 2.4491. Min Act: -0.0001
Data Index: 635090 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4651. Min Range: -2.4651
Max Act: 2.4308. Min Act: -0.0001
Data Index: 1568199 (Python Code)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4651. Min Range: -2.4651
Max Act: 2.4331. Min Act: -0.0001
Data Index: 1384435 (Python Code)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4651. Min Range: -2.4651
Max Act: 2.2671. Min Act: -0.0001
Data Index: 1641636 (Python Code)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4651. Min Range: -2.4651
Max Act: 2.2570. Min Act: -0.0001
Data Index: 1542802 (Python Code)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4651. Min Range: -2.4651
Max Act: 2.3641. Min Act: -0.0001
Data Index: 1513309 (Python Code)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4651. Min Range: -2.4651
Max Act: 2.3367. Min Act: -0.0001
Data Index: 876978 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4651. Min Range: -2.4651
Max Act: 2.3353. Min Act: -0.0001
Data Index: 400070 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4651. Min Range: -2.4651
Max Act: 2.3113. Min Act: -0.0001
Data Index: 671899 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4651. Min Range: -2.4651
Max Act: 2.1976. Min Act: -0.0001
Data Index: 512565 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4651. Min Range: -2.4651
Max Act: 2.2840. Min Act: -0.0001
Data Index: 1249959 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4651. Min Range: -2.4651
Max Act: 2.1345. Min Act: -0.0001
Data Index: 1437922 (Python Code)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4651. Min Range: -2.4651
Max Act: 2.2412. Min Act: -0.0001
Data Index: 1269653 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4651. Min Range: -2.4651
Max Act: 2.2414. Min Act: -0.0001
Data Index: 1644830 (Python Code)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4651. Min Range: -2.4651
Max Act: 2.4651. Min Act: -0.0001
Data Index: 672821 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4651. Min Range: -2.4651
Max Act: 2.2272. Min Act: -0.0001
Data Index: 1447296 (Python Code)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4651. Min Range: -2.4651
Max Act: 2.0895. Min Act: -0.0001
Data Index: 1389261 (Python Code)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4651. Min Range: -2.4651
Max Act: 2.0570. Min Act: -0.0001
Data Index: 276233 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4651. Min Range: -2.4651
Max Act: 2.0581. Min Act: -0.0001
Data Index: 1394977 (Python Code)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4651. Min Range: -2.4651
Max Act: 2.0672. Min Act: -0.0001
Data Index: 72366 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19