Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2780 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.3246. Min Range: -2.3246
Max Act: 2.3246. Min Act: -0.0001
Data Index: 944742 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3246. Min Range: -2.3246
Max Act: 2.1004. Min Act: -0.0001
Data Index: 985570 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3246. Min Range: -2.3246
Max Act: 2.1810. Min Act: -0.0001
Data Index: 1245164 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3246. Min Range: -2.3246
Max Act: 2.0210. Min Act: -0.0001
Data Index: 392378 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3246. Min Range: -2.3246
Max Act: 2.2504. Min Act: -0.0001
Data Index: 1321053 (C4 (Web Text))
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3246. Min Range: -2.3246
Max Act: 2.1279. Min Act: -0.0001
Data Index: 319880 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3246. Min Range: -2.3246
Max Act: 1.7985. Min Act: -0.0001
Data Index: 665159 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3246. Min Range: -2.3246
Max Act: 1.9415. Min Act: -0.0001
Data Index: 577376 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3246. Min Range: -2.3246
Max Act: 2.0499. Min Act: -0.0001
Data Index: 460954 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3246. Min Range: -2.3246
Max Act: 2.0403. Min Act: -0.0001
Data Index: 750298 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3246. Min Range: -2.3246
Max Act: 1.7750. Min Act: -0.0001
Data Index: 606260 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3246. Min Range: -2.3246
Max Act: 1.8291. Min Act: -0.0001
Data Index: 1144851 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3246. Min Range: -2.3246
Max Act: 1.8442. Min Act: -0.0001
Data Index: 1162167 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3246. Min Range: -2.3246
Max Act: 1.7058. Min Act: -0.0001
Data Index: 835104 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3246. Min Range: -2.3246
Max Act: 1.8864. Min Act: -0.0001
Data Index: 205371 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3246. Min Range: -2.3246
Max Act: 1.8112. Min Act: -0.0001
Data Index: 1263516 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3246. Min Range: -2.3246
Max Act: 1.7783. Min Act: -0.0001
Data Index: 245041 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3246. Min Range: -2.3246
Max Act: 1.6963. Min Act: -0.0001
Data Index: 431015 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3246. Min Range: -2.3246
Max Act: 1.7890. Min Act: -0.0001
Data Index: 1344032 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3246. Min Range: -2.3246
Max Act: 1.6812. Min Act: -0.0001
Data Index: 362392 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19