Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 23 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.9647. Min Range: -2.9647
Max Act: 2.9647. Min Act: -0.0001
Data Index: 585830 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9647. Min Range: -2.9647
Max Act: 2.6794. Min Act: -0.0001
Data Index: 1282209 (C4 (Web Text))
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9647. Min Range: -2.9647
Max Act: 2.6215. Min Act: -0.0001
Data Index: 1132971 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9647. Min Range: -2.9647
Max Act: 2.7286. Min Act: -0.0001
Data Index: 266609 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9647. Min Range: -2.9647
Max Act: 2.2232. Min Act: -0.0001
Data Index: 1167627 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9647. Min Range: -2.9647
Max Act: 2.1246. Min Act: -0.0001
Data Index: 791611 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9647. Min Range: -2.9647
Max Act: 2.2291. Min Act: -0.0001
Data Index: 427465 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9647. Min Range: -2.9647
Max Act: 2.1661. Min Act: -0.0001
Data Index: 504867 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9647. Min Range: -2.9647
Max Act: 1.9930. Min Act: -0.0001
Data Index: 1055304 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9647. Min Range: -2.9647
Max Act: 2.0830. Min Act: -0.0001
Data Index: 996140 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9647. Min Range: -2.9647
Max Act: 2.1470. Min Act: -0.0001
Data Index: 386379 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9647. Min Range: -2.9647
Max Act: 2.0503. Min Act: -0.0001
Data Index: 1356713 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9647. Min Range: -2.9647
Max Act: 2.0699. Min Act: -0.0001
Data Index: 642469 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9647. Min Range: -2.9647
Max Act: 2.0480. Min Act: -0.0001
Data Index: 255682 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9647. Min Range: -2.9647
Max Act: 1.9492. Min Act: -0.0001
Data Index: 984497 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9647. Min Range: -2.9647
Max Act: 2.1512. Min Act: -0.0001
Data Index: 327429 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9647. Min Range: -2.9647
Max Act: 1.9902. Min Act: -0.0001
Data Index: 596939 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9647. Min Range: -2.9647
Max Act: 1.8669. Min Act: -0.0001
Data Index: 965560 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9647. Min Range: -2.9647
Max Act: 1.9599. Min Act: -0.0001
Data Index: 277883 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9647. Min Range: -2.9647
Max Act: 2.0532. Min Act: -0.0001
Data Index: 482373 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19