Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 663 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.2650. Min Range: -2.2650
Max Act: 2.0081. Min Act: -0.0001
Data Index: 960243 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2650. Min Range: -2.2650
Max Act: 2.2650. Min Act: -0.0002
Data Index: 1269593 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2650. Min Range: -2.2650
Max Act: 2.1300. Min Act: -0.0001
Data Index: 775418 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2650. Min Range: -2.2650
Max Act: 2.0057. Min Act: -0.0001
Data Index: 296049 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2650. Min Range: -2.2650
Max Act: 1.7877. Min Act: -0.0001
Data Index: 1342391 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2650. Min Range: -2.2650
Max Act: 1.9316. Min Act: -0.0002
Data Index: 194996 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2650. Min Range: -2.2650
Max Act: 1.9393. Min Act: -0.0001
Data Index: 590029 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2650. Min Range: -2.2650
Max Act: 1.9165. Min Act: -0.0001
Data Index: 318896 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2650. Min Range: -2.2650
Max Act: 1.8954. Min Act: -0.0001
Data Index: 1207188 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2650. Min Range: -2.2650
Max Act: 1.7303. Min Act: -0.0001
Data Index: 148476 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2650. Min Range: -2.2650
Max Act: 2.0834. Min Act: -0.0002
Data Index: 651795 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2650. Min Range: -2.2650
Max Act: 1.8666. Min Act: -0.0001
Data Index: 554605 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2650. Min Range: -2.2650
Max Act: 1.9829. Min Act: -0.0001
Data Index: 796794 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2650. Min Range: -2.2650
Max Act: 1.7219. Min Act: -0.0001
Data Index: 269415 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2650. Min Range: -2.2650
Max Act: 2.0010. Min Act: -0.0001
Data Index: 101696 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2650. Min Range: -2.2650
Max Act: 1.8257. Min Act: -0.0002
Data Index: 746166 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2650. Min Range: -2.2650
Max Act: 1.7994. Min Act: -0.0002
Data Index: 930077 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2650. Min Range: -2.2650
Max Act: 1.6148. Min Act: -0.0001
Data Index: 423095 (C4 (Web Text))
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2650. Min Range: -2.2650
Max Act: 1.7980. Min Act: -0.0001
Data Index: 166151 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2650. Min Range: -2.2650
Max Act: 1.8236. Min Act: -0.0001
Data Index: 1135279 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19