Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1470 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 4.3218. Min Range: -4.3218
Max Act: 4.3218. Min Act: -0.0000
Data Index: 430258 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3218. Min Range: -4.3218
Max Act: 3.9324. Min Act: -0.0001
Data Index: 97047 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3218. Min Range: -4.3218
Max Act: 3.6538. Min Act: -0.0001
Data Index: 211485 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3218. Min Range: -4.3218
Max Act: 3.4409. Min Act: -0.0001
Data Index: 622215 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3218. Min Range: -4.3218
Max Act: 3.2446. Min Act: -0.0001
Data Index: 696414 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3218. Min Range: -4.3218
Max Act: 3.0311. Min Act: -0.0001
Data Index: 177041 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3218. Min Range: -4.3218
Max Act: 2.9972. Min Act: -0.0001
Data Index: 993796 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3218. Min Range: -4.3218
Max Act: 2.9806. Min Act: -0.0001
Data Index: 1299105 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3218. Min Range: -4.3218
Max Act: 2.9818. Min Act: -0.0001
Data Index: 515035 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3218. Min Range: -4.3218
Max Act: 3.0965. Min Act: -0.0001
Data Index: 1151284 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3218. Min Range: -4.3218
Max Act: 2.9327. Min Act: -0.0000
Data Index: 695195 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3218. Min Range: -4.3218
Max Act: 2.7749. Min Act: -0.0001
Data Index: 840747 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3218. Min Range: -4.3218
Max Act: 2.8867. Min Act: -0.0001
Data Index: 150870 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3218. Min Range: -4.3218
Max Act: 2.7576. Min Act: -0.0000
Data Index: 1314087 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3218. Min Range: -4.3218
Max Act: 2.8749. Min Act: -0.0001
Data Index: 1574500 (Python Code)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3218. Min Range: -4.3218
Max Act: 2.6075. Min Act: -0.0001
Data Index: 1328004 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3218. Min Range: -4.3218
Max Act: 2.7047. Min Act: -0.0001
Data Index: 1500118 (Python Code)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3218. Min Range: -4.3218
Max Act: 2.5536. Min Act: -0.0001
Data Index: 132728 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3218. Min Range: -4.3218
Max Act: 2.6693. Min Act: -0.0000
Data Index: 292821 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3218. Min Range: -4.3218
Max Act: 2.6632. Min Act: -0.0001
Data Index: 1247230 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19