Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1920 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.3926. Min Range: -2.3926
Max Act: 2.2225. Min Act: -0.0001
Data Index: 644242 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3926. Min Range: -2.3926
Max Act: 2.3926. Min Act: -0.0001
Data Index: 50718 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3926. Min Range: -2.3926
Max Act: 2.1826. Min Act: -0.0001
Data Index: 404422 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3926. Min Range: -2.3926
Max Act: 2.2764. Min Act: -0.0001
Data Index: 45250 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3926. Min Range: -2.3926
Max Act: 2.1281. Min Act: -0.0001
Data Index: 320410 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3926. Min Range: -2.3926
Max Act: 1.9592. Min Act: -0.0001
Data Index: 1003265 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3926. Min Range: -2.3926
Max Act: 1.7293. Min Act: -0.0001
Data Index: 816507 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3926. Min Range: -2.3926
Max Act: 1.9541. Min Act: -0.0001
Data Index: 593184 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3926. Min Range: -2.3926
Max Act: 1.7636. Min Act: -0.0001
Data Index: 724536 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3926. Min Range: -2.3926
Max Act: 1.8462. Min Act: -0.0001
Data Index: 867117 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3926. Min Range: -2.3926
Max Act: 1.7764. Min Act: -0.0001
Data Index: 1283502 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3926. Min Range: -2.3926
Max Act: 1.7778. Min Act: -0.0001
Data Index: 984124 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3926. Min Range: -2.3926
Max Act: 1.7743. Min Act: -0.0001
Data Index: 72711 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3926. Min Range: -2.3926
Max Act: 1.7089. Min Act: -0.0001
Data Index: 574922 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3926. Min Range: -2.3926
Max Act: 1.7001. Min Act: -0.0001
Data Index: 1106048 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3926. Min Range: -2.3926
Max Act: 1.7508. Min Act: -0.0001
Data Index: 1340201 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3926. Min Range: -2.3926
Max Act: 1.7986. Min Act: -0.0001
Data Index: 13502 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3926. Min Range: -2.3926
Max Act: 1.6645. Min Act: -0.0001
Data Index: 429299 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3926. Min Range: -2.3926
Max Act: 1.8624. Min Act: -0.0001
Data Index: 309986 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3926. Min Range: -2.3926
Max Act: 1.6927. Min Act: -0.0001
Data Index: 706707 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19