Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2087 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.8535. Min Range: -3.8535
Max Act: 3.7159. Min Act: -0.0001
Data Index: 1329776 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8535. Min Range: -3.8535
Max Act: 3.8535. Min Act: -0.0001
Data Index: 485370 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8535. Min Range: -3.8535
Max Act: 3.3754. Min Act: -0.0001
Data Index: 96444 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8535. Min Range: -3.8535
Max Act: 3.0965. Min Act: -0.0001
Data Index: 377658 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8535. Min Range: -3.8535
Max Act: 2.8723. Min Act: -0.0001
Data Index: 423124 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8535. Min Range: -3.8535
Max Act: 2.8485. Min Act: -0.0001
Data Index: 943121 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8535. Min Range: -3.8535
Max Act: 2.8180. Min Act: -0.0001
Data Index: 411908 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8535. Min Range: -3.8535
Max Act: 3.0597. Min Act: -0.0001
Data Index: 670076 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8535. Min Range: -3.8535
Max Act: 2.5783. Min Act: -0.0001
Data Index: 225961 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8535. Min Range: -3.8535
Max Act: 2.4430. Min Act: -0.0001
Data Index: 903549 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8535. Min Range: -3.8535
Max Act: 2.5774. Min Act: -0.0001
Data Index: 1020257 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8535. Min Range: -3.8535
Max Act: 2.2447. Min Act: -0.0001
Data Index: 1225438 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8535. Min Range: -3.8535
Max Act: 2.7110. Min Act: -0.0001
Data Index: 1174061 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8535. Min Range: -3.8535
Max Act: 2.5703. Min Act: -0.0001
Data Index: 194652 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8535. Min Range: -3.8535
Max Act: 2.5357. Min Act: -0.0001
Data Index: 379229 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8535. Min Range: -3.8535
Max Act: 2.7757. Min Act: -0.0001
Data Index: 987281 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8535. Min Range: -3.8535
Max Act: 2.2632. Min Act: -0.0001
Data Index: 1170753 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8535. Min Range: -3.8535
Max Act: 2.7891. Min Act: -0.0001
Data Index: 1106571 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8535. Min Range: -3.8535
Max Act: 2.8670. Min Act: -0.0001
Data Index: 126393 (C4 (Web Text))
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8535. Min Range: -3.8535
Max Act: 2.7467. Min Act: -0.0001
Data Index: 322536 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19