Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1943 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.3523. Min Range: -1.3523
Max Act: 1.3456. Min Act: -0.0001
Data Index: 819502 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3523. Min Range: -1.3523
Max Act: 1.3394. Min Act: -0.0001
Data Index: 594097 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3523. Min Range: -1.3523
Max Act: 1.3462. Min Act: -0.0001
Data Index: 334533 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3523. Min Range: -1.3523
Max Act: 1.2457. Min Act: -0.0001
Data Index: 561528 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3523. Min Range: -1.3523
Max Act: 1.3523. Min Act: -0.0001
Data Index: 400074 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3523. Min Range: -1.3523
Max Act: 1.1832. Min Act: -0.0001
Data Index: 95351 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3523. Min Range: -1.3523
Max Act: 1.2793. Min Act: -0.0001
Data Index: 971446 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3523. Min Range: -1.3523
Max Act: 1.2937. Min Act: -0.0001
Data Index: 1055773 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3523. Min Range: -1.3523
Max Act: 1.1876. Min Act: -0.0001
Data Index: 1086124 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3523. Min Range: -1.3523
Max Act: 1.1570. Min Act: -0.0001
Data Index: 1224256 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3523. Min Range: -1.3523
Max Act: 1.0775. Min Act: -0.0001
Data Index: 447575 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3523. Min Range: -1.3523
Max Act: 1.2642. Min Act: -0.0001
Data Index: 506239 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3523. Min Range: -1.3523
Max Act: 1.0612. Min Act: -0.0001
Data Index: 1286988 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3523. Min Range: -1.3523
Max Act: 1.1367. Min Act: -0.0001
Data Index: 97521 (C4 (Web Text))
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3523. Min Range: -1.3523
Max Act: 1.0676. Min Act: -0.0001
Data Index: 1338328 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3523. Min Range: -1.3523
Max Act: 1.0785. Min Act: -0.0001
Data Index: 123083 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3523. Min Range: -1.3523
Max Act: 0.9228. Min Act: -0.0001
Data Index: 1165431 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3523. Min Range: -1.3523
Max Act: 1.0361. Min Act: -0.0001
Data Index: 645003 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3523. Min Range: -1.3523
Max Act: 1.1627. Min Act: -0.0001
Data Index: 1286962 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3523. Min Range: -1.3523
Max Act: 0.9822. Min Act: -0.0001
Data Index: 771400 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19