Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1820 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.3765. Min Range: -0.3765
Max Act: 0.3765. Min Act: -0.0001
Data Index: 670983 (C4 (Web Text))
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.3765. Min Range: -0.3765
Max Act: 0.3500. Min Act: -0.0001
Data Index: 393393 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.3765. Min Range: -0.3765
Max Act: 0.3506. Min Act: -0.0001
Data Index: 1043016 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.3765. Min Range: -0.3765
Max Act: 0.3456. Min Act: -0.0001
Data Index: 711341 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.3765. Min Range: -0.3765
Max Act: 0.3510. Min Act: -0.0001
Data Index: 1095230 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.3765. Min Range: -0.3765
Max Act: 0.3412. Min Act: -0.0001
Data Index: 831922 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.3765. Min Range: -0.3765
Max Act: 0.3248. Min Act: -0.0001
Data Index: 1353481 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.3765. Min Range: -0.3765
Max Act: 0.3449. Min Act: -0.0001
Data Index: 749057 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.3765. Min Range: -0.3765
Max Act: 0.3215. Min Act: -0.0001
Data Index: 462399 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.3765. Min Range: -0.3765
Max Act: 0.3159. Min Act: -0.0001
Data Index: 616551 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.3765. Min Range: -0.3765
Max Act: 0.3190. Min Act: -0.0001
Data Index: 465526 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.3765. Min Range: -0.3765
Max Act: 0.3195. Min Act: -0.0001
Data Index: 716749 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.3765. Min Range: -0.3765
Max Act: 0.3132. Min Act: -0.0001
Data Index: 1009680 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.3765. Min Range: -0.3765
Max Act: 0.2998. Min Act: -0.0001
Data Index: 404307 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.3765. Min Range: -0.3765
Max Act: 0.3099. Min Act: -0.0001
Data Index: 1001534 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.3765. Min Range: -0.3765
Max Act: 0.3066. Min Act: -0.0001
Data Index: 171105 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.3765. Min Range: -0.3765
Max Act: 0.2944. Min Act: -0.0001
Data Index: 813437 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.3765. Min Range: -0.3765
Max Act: 0.2922. Min Act: -0.0001
Data Index: 426947 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.3765. Min Range: -0.3765
Max Act: 0.2967. Min Act: -0.0001
Data Index: 543094 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.3765. Min Range: -0.3765
Max Act: 0.2780. Min Act: -0.0001
Data Index: 315303 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19