Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2904 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.3784. Min Range: -2.3784
Max Act: 2.3784. Min Act: -0.0001
Data Index: 1229113 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3784. Min Range: -2.3784
Max Act: 2.0425. Min Act: -0.0001
Data Index: 1163372 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3784. Min Range: -2.3784
Max Act: 2.1787. Min Act: -0.0001
Data Index: 739809 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3784. Min Range: -2.3784
Max Act: 1.8536. Min Act: -0.0001
Data Index: 1276789 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3784. Min Range: -2.3784
Max Act: 1.9532. Min Act: -0.0001
Data Index: 392199 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3784. Min Range: -2.3784
Max Act: 1.9456. Min Act: -0.0001
Data Index: 2905 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3784. Min Range: -2.3784
Max Act: 1.8503. Min Act: -0.0001
Data Index: 750499 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3784. Min Range: -2.3784
Max Act: 1.8865. Min Act: -0.0001
Data Index: 238770 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3784. Min Range: -2.3784
Max Act: 1.8373. Min Act: -0.0001
Data Index: 1047816 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3784. Min Range: -2.3784
Max Act: 1.7452. Min Act: -0.0001
Data Index: 184961 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3784. Min Range: -2.3784
Max Act: 1.9499. Min Act: -0.0001
Data Index: 765415 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3784. Min Range: -2.3784
Max Act: 1.6667. Min Act: -0.0001
Data Index: 342834 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3784. Min Range: -2.3784
Max Act: 1.8766. Min Act: -0.0001
Data Index: 1040119 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3784. Min Range: -2.3784
Max Act: 1.7638. Min Act: -0.0001
Data Index: 485225 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3784. Min Range: -2.3784
Max Act: 1.8752. Min Act: -0.0001
Data Index: 854873 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3784. Min Range: -2.3784
Max Act: 1.6709. Min Act: -0.0001
Data Index: 806033 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3784. Min Range: -2.3784
Max Act: 1.7297. Min Act: -0.0001
Data Index: 859389 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3784. Min Range: -2.3784
Max Act: 1.7078. Min Act: -0.0001
Data Index: 1067469 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3784. Min Range: -2.3784
Max Act: 1.7664. Min Act: -0.0001
Data Index: 441920 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3784. Min Range: -2.3784
Max Act: 1.9162. Min Act: -0.0001
Data Index: 368846 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19