Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4125 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.0508. Min Range: -3.0508
Max Act: 3.0508. Min Act: -0.0001
Data Index: 1304269 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0508. Min Range: -3.0508
Max Act: 2.7297. Min Act: -0.0001
Data Index: 666392 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0508. Min Range: -3.0508
Max Act: 2.6520. Min Act: -0.0001
Data Index: 1065972 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0508. Min Range: -3.0508
Max Act: 2.6167. Min Act: -0.0001
Data Index: 515229 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0508. Min Range: -3.0508
Max Act: 2.4526. Min Act: -0.0001
Data Index: 1336106 (C4 (Web Text))
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0508. Min Range: -3.0508
Max Act: 2.3258. Min Act: -0.0001
Data Index: 651116 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0508. Min Range: -3.0508
Max Act: 2.1811. Min Act: -0.0001
Data Index: 1355929 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0508. Min Range: -3.0508
Max Act: 2.4090. Min Act: -0.0001
Data Index: 501210 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0508. Min Range: -3.0508
Max Act: 2.1658. Min Act: -0.0001
Data Index: 91304 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0508. Min Range: -3.0508
Max Act: 2.3529. Min Act: -0.0001
Data Index: 146693 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0508. Min Range: -3.0508
Max Act: 2.2083. Min Act: -0.0001
Data Index: 1180155 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0508. Min Range: -3.0508
Max Act: 1.9707. Min Act: -0.0001
Data Index: 811000 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0508. Min Range: -3.0508
Max Act: 2.0369. Min Act: -0.0001
Data Index: 530716 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0508. Min Range: -3.0508
Max Act: 1.9249. Min Act: -0.0001
Data Index: 767135 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0508. Min Range: -3.0508
Max Act: 1.7340. Min Act: -0.0001
Data Index: 1261379 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0508. Min Range: -3.0508
Max Act: 2.0097. Min Act: -0.0001
Data Index: 1153696 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0508. Min Range: -3.0508
Max Act: 1.8123. Min Act: -0.0001
Data Index: 191407 (C4 (Web Text))
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0508. Min Range: -3.0508
Max Act: 1.8987. Min Act: -0.0001
Data Index: 1339678 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0508. Min Range: -3.0508
Max Act: 1.8926. Min Act: -0.0001
Data Index: 569630 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0508. Min Range: -3.0508
Max Act: 1.8461. Min Act: -0.0001
Data Index: 389041 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19