Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3971 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.4857. Min Range: -2.4857
Max Act: 2.4857. Min Act: -0.0001
Data Index: 1318575 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4857. Min Range: -2.4857
Max Act: 2.3924. Min Act: -0.0001
Data Index: 1254268 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4857. Min Range: -2.4857
Max Act: 2.1188. Min Act: -0.0001
Data Index: 509317 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4857. Min Range: -2.4857
Max Act: 2.1965. Min Act: -0.0001
Data Index: 1123448 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4857. Min Range: -2.4857
Max Act: 2.1339. Min Act: -0.0001
Data Index: 1291406 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4857. Min Range: -2.4857
Max Act: 2.0416. Min Act: -0.0001
Data Index: 450324 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4857. Min Range: -2.4857
Max Act: 1.9049. Min Act: -0.0001
Data Index: 1026400 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4857. Min Range: -2.4857
Max Act: 1.9514. Min Act: -0.0001
Data Index: 616168 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4857. Min Range: -2.4857
Max Act: 1.8353. Min Act: -0.0001
Data Index: 722890 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4857. Min Range: -2.4857
Max Act: 1.7782. Min Act: -0.0001
Data Index: 1166250 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4857. Min Range: -2.4857
Max Act: 1.8702. Min Act: -0.0001
Data Index: 1191291 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4857. Min Range: -2.4857
Max Act: 1.8042. Min Act: -0.0001
Data Index: 109222 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4857. Min Range: -2.4857
Max Act: 1.8940. Min Act: -0.0001
Data Index: 665691 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4857. Min Range: -2.4857
Max Act: 1.8751. Min Act: -0.0001
Data Index: 954955 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4857. Min Range: -2.4857
Max Act: 1.7390. Min Act: -0.0001
Data Index: 190177 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4857. Min Range: -2.4857
Max Act: 1.8014. Min Act: -0.0001
Data Index: 403221 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4857. Min Range: -2.4857
Max Act: 1.7797. Min Act: -0.0001
Data Index: 988317 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4857. Min Range: -2.4857
Max Act: 1.7749. Min Act: -0.0001
Data Index: 1088444 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4857. Min Range: -2.4857
Max Act: 1.7752. Min Act: -0.0001
Data Index: 1147899 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4857. Min Range: -2.4857
Max Act: 1.7073. Min Act: -0.0001
Data Index: 1332563 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19