Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3785 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.5988. Min Range: -2.5988
Max Act: 2.4012. Min Act: -0.0001
Data Index: 340752 (C4 (Web Text))
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5988. Min Range: -2.5988
Max Act: 2.5988. Min Act: -0.0001
Data Index: 824050 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5988. Min Range: -2.5988
Max Act: 2.4737. Min Act: -0.0001
Data Index: 1286768 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5988. Min Range: -2.5988
Max Act: 2.4278. Min Act: -0.0001
Data Index: 718963 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5988. Min Range: -2.5988
Max Act: 2.4136. Min Act: -0.0001
Data Index: 1196673 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5988. Min Range: -2.5988
Max Act: 2.0170. Min Act: -0.0001
Data Index: 255556 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5988. Min Range: -2.5988
Max Act: 2.2008. Min Act: -0.0001
Data Index: 305544 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5988. Min Range: -2.5988
Max Act: 2.2700. Min Act: -0.0001
Data Index: 169972 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5988. Min Range: -2.5988
Max Act: 2.0503. Min Act: -0.0001
Data Index: 227429 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5988. Min Range: -2.5988
Max Act: 2.1300. Min Act: -0.0001
Data Index: 471056 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5988. Min Range: -2.5988
Max Act: 2.0516. Min Act: -0.0001
Data Index: 77031 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5988. Min Range: -2.5988
Max Act: 1.9205. Min Act: -0.0001
Data Index: 1201572 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5988. Min Range: -2.5988
Max Act: 2.0054. Min Act: -0.0001
Data Index: 794680 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5988. Min Range: -2.5988
Max Act: 2.0764. Min Act: -0.0001
Data Index: 255076 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5988. Min Range: -2.5988
Max Act: 1.9668. Min Act: -0.0001
Data Index: 1281173 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5988. Min Range: -2.5988
Max Act: 1.9497. Min Act: -0.0001
Data Index: 1380589 (Python Code)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5988. Min Range: -2.5988
Max Act: 1.9489. Min Act: -0.0001
Data Index: 769113 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5988. Min Range: -2.5988
Max Act: 1.9386. Min Act: -0.0001
Data Index: 23805 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5988. Min Range: -2.5988
Max Act: 2.1274. Min Act: -0.0001
Data Index: 838637 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5988. Min Range: -2.5988
Max Act: 1.9207. Min Act: -0.0001
Data Index: 417267 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19