Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2557 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.7240. Min Act: -0.0001
Data Index: 1227354 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.6289. Min Act: -0.0001
Data Index: 1074476 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.6263. Min Act: -0.0001
Data Index: 1257599 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.6048. Min Act: -0.0001
Data Index: 238179 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.5732. Min Act: -0.0001
Data Index: 704203 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.2061. Min Act: -0.0001
Data Index: 920422 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.3575. Min Act: -0.0001
Data Index: 411182 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.3628. Min Act: -0.0001
Data Index: 631648 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.5011. Min Act: -0.0001
Data Index: 468888 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.3419. Min Act: -0.0001
Data Index: 1344832 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.3516. Min Act: -0.0001
Data Index: 1322711 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.1863. Min Act: -0.0001
Data Index: 1056527 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.1611. Min Act: -0.0001
Data Index: 953698 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.1656. Min Act: -0.0001
Data Index: 571121 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.3084. Min Act: -0.0001
Data Index: 696800 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.3092. Min Act: -0.0001
Data Index: 150138 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.4085. Min Act: -0.0001
Data Index: 386026 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.2226. Min Act: -0.0001
Data Index: 452520 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.1668. Min Act: -0.0001
Data Index: 19581 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.1909. Min Act: -0.0001
Data Index: 597870 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19