Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2287 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.5023. Min Range: -1.5023
Max Act: 1.5023. Min Act: -0.0001
Data Index: 146050 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5023. Min Range: -1.5023
Max Act: 1.3520. Min Act: -0.0001
Data Index: 649977 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5023. Min Range: -1.5023
Max Act: 1.2864. Min Act: -0.0001
Data Index: 981647 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5023. Min Range: -1.5023
Max Act: 1.2557. Min Act: -0.0001
Data Index: 516710 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5023. Min Range: -1.5023
Max Act: 1.2482. Min Act: -0.0001
Data Index: 136193 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5023. Min Range: -1.5023
Max Act: 1.2069. Min Act: -0.0001
Data Index: 1316950 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5023. Min Range: -1.5023
Max Act: 1.2125. Min Act: -0.0001
Data Index: 437185 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5023. Min Range: -1.5023
Max Act: 1.2386. Min Act: -0.0001
Data Index: 622845 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5023. Min Range: -1.5023
Max Act: 1.2603. Min Act: -0.0001
Data Index: 589731 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5023. Min Range: -1.5023
Max Act: 1.2121. Min Act: -0.0001
Data Index: 992620 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5023. Min Range: -1.5023
Max Act: 1.1955. Min Act: -0.0001
Data Index: 140239 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5023. Min Range: -1.5023
Max Act: 1.1242. Min Act: -0.0001
Data Index: 716932 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5023. Min Range: -1.5023
Max Act: 1.1813. Min Act: -0.0001
Data Index: 1116235 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5023. Min Range: -1.5023
Max Act: 1.1936. Min Act: -0.0001
Data Index: 711917 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5023. Min Range: -1.5023
Max Act: 1.1409. Min Act: -0.0001
Data Index: 495077 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5023. Min Range: -1.5023
Max Act: 1.2044. Min Act: -0.0001
Data Index: 627610 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5023. Min Range: -1.5023
Max Act: 1.1447. Min Act: -0.0001
Data Index: 848492 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5023. Min Range: -1.5023
Max Act: 1.1408. Min Act: -0.0001
Data Index: 1100361 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5023. Min Range: -1.5023
Max Act: 1.1398. Min Act: -0.0001
Data Index: 650171 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5023. Min Range: -1.5023
Max Act: 1.1002. Min Act: -0.0001
Data Index: 418566 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19