Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3665 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.1730. Min Range: -2.1730
Max Act: 2.1730. Min Act: -0.0001
Data Index: 1017820 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1730. Min Range: -2.1730
Max Act: 2.1730. Min Act: -0.0001
Data Index: 1443073 (Python Code)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1730. Min Range: -2.1730
Max Act: 1.6519. Min Act: -0.0001
Data Index: 1350115 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1730. Min Range: -2.1730
Max Act: 1.5025. Min Act: -0.0001
Data Index: 1316898 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1730. Min Range: -2.1730
Max Act: 1.5868. Min Act: -0.0001
Data Index: 652899 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1730. Min Range: -2.1730
Max Act: 1.4805. Min Act: -0.0001
Data Index: 931422 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1730. Min Range: -2.1730
Max Act: 1.5229. Min Act: -0.0001
Data Index: 681610 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1730. Min Range: -2.1730
Max Act: 1.4991. Min Act: -0.0001
Data Index: 39028 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1730. Min Range: -2.1730
Max Act: 1.5027. Min Act: -0.0001
Data Index: 22336 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1730. Min Range: -2.1730
Max Act: 1.4856. Min Act: -0.0001
Data Index: 1008375 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1730. Min Range: -2.1730
Max Act: 1.5462. Min Act: -0.0001
Data Index: 1111510 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1730. Min Range: -2.1730
Max Act: 1.5401. Min Act: -0.0001
Data Index: 350825 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1730. Min Range: -2.1730
Max Act: 1.4214. Min Act: -0.0001
Data Index: 117241 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1730. Min Range: -2.1730
Max Act: 1.3279. Min Act: -0.0001
Data Index: 130030 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1730. Min Range: -2.1730
Max Act: 1.4843. Min Act: -0.0001
Data Index: 147020 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1730. Min Range: -2.1730
Max Act: 1.3469. Min Act: -0.0001
Data Index: 851335 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1730. Min Range: -2.1730
Max Act: 1.3386. Min Act: -0.0001
Data Index: 676360 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1730. Min Range: -2.1730
Max Act: 1.1705. Min Act: -0.0001
Data Index: 1398760 (Python Code)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1730. Min Range: -2.1730
Max Act: 1.2755. Min Act: -0.0001
Data Index: 703145 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1730. Min Range: -2.1730
Max Act: 1.2493. Min Act: -0.0001
Data Index: 556580 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19