Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2708 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.6294. Min Range: -3.6294
Max Act: 3.6294. Min Act: -0.0001
Data Index: 18426 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6294. Min Range: -3.6294
Max Act: 3.6195. Min Act: -0.0001
Data Index: 755293 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6294. Min Range: -3.6294
Max Act: 2.3375. Min Act: -0.0001
Data Index: 622038 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6294. Min Range: -3.6294
Max Act: 2.5764. Min Act: -0.0001
Data Index: 1346674 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6294. Min Range: -3.6294
Max Act: 2.3954. Min Act: -0.0001
Data Index: 335009 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6294. Min Range: -3.6294
Max Act: 2.3386. Min Act: -0.0001
Data Index: 516794 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6294. Min Range: -3.6294
Max Act: 2.3963. Min Act: -0.0001
Data Index: 271334 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6294. Min Range: -3.6294
Max Act: 2.1612. Min Act: -0.0001
Data Index: 486905 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6294. Min Range: -3.6294
Max Act: 2.3338. Min Act: -0.0001
Data Index: 1206199 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6294. Min Range: -3.6294
Max Act: 2.0563. Min Act: -0.0001
Data Index: 13226 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6294. Min Range: -3.6294
Max Act: 2.1322. Min Act: -0.0001
Data Index: 1074254 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6294. Min Range: -3.6294
Max Act: 2.1974. Min Act: -0.0001
Data Index: 143141 (C4 (Web Text))
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6294. Min Range: -3.6294
Max Act: 1.9818. Min Act: -0.0001
Data Index: 153431 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6294. Min Range: -3.6294
Max Act: 1.8770. Min Act: -0.0001
Data Index: 381765 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6294. Min Range: -3.6294
Max Act: 2.0550. Min Act: -0.0002
Data Index: 41793 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6294. Min Range: -3.6294
Max Act: 2.1589. Min Act: -0.0001
Data Index: 917928 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6294. Min Range: -3.6294
Max Act: 2.0610. Min Act: -0.0001
Data Index: 110727 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6294. Min Range: -3.6294
Max Act: 2.1217. Min Act: -0.0001
Data Index: 853240 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6294. Min Range: -3.6294
Max Act: 1.9079. Min Act: -0.0001
Data Index: 817853 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6294. Min Range: -3.6294
Max Act: 1.9873. Min Act: -0.0001
Data Index: 1297793 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19