Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 544 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.8321. Min Range: -0.8321
Max Act: 0.8321. Min Act: -0.0001
Data Index: 1108579 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8321. Min Range: -0.8321
Max Act: 0.7883. Min Act: -0.0001
Data Index: 1322857 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8321. Min Range: -0.8321
Max Act: 0.8130. Min Act: -0.0001
Data Index: 629841 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8321. Min Range: -0.8321
Max Act: 0.8210. Min Act: -0.0001
Data Index: 523495 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8321. Min Range: -0.8321
Max Act: 0.7604. Min Act: -0.0001
Data Index: 232066 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8321. Min Range: -0.8321
Max Act: 0.7997. Min Act: -0.0001
Data Index: 857154 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8321. Min Range: -0.8321
Max Act: 0.7077. Min Act: -0.0001
Data Index: 212905 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8321. Min Range: -0.8321
Max Act: 0.7421. Min Act: -0.0001
Data Index: 749989 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8321. Min Range: -0.8321
Max Act: 0.7040. Min Act: -0.0001
Data Index: 709149 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8321. Min Range: -0.8321
Max Act: 0.6477. Min Act: -0.0001
Data Index: 587564 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8321. Min Range: -0.8321
Max Act: 0.6785. Min Act: -0.0001
Data Index: 95064 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8321. Min Range: -0.8321
Max Act: 0.7207. Min Act: -0.0001
Data Index: 728624 (C4 (Web Text))
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8321. Min Range: -0.8321
Max Act: 0.6907. Min Act: -0.0001
Data Index: 33994 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8321. Min Range: -0.8321
Max Act: 0.6713. Min Act: -0.0001
Data Index: 645533 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8321. Min Range: -0.8321
Max Act: 0.6995. Min Act: -0.0001
Data Index: 490317 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8321. Min Range: -0.8321
Max Act: 0.6507. Min Act: -0.0001
Data Index: 1222710 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8321. Min Range: -0.8321
Max Act: 0.6879. Min Act: -0.0001
Data Index: 125288 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8321. Min Range: -0.8321
Max Act: 0.6619. Min Act: -0.0001
Data Index: 1243518 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8321. Min Range: -0.8321
Max Act: 0.6523. Min Act: -0.0001
Data Index: 729379 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8321. Min Range: -0.8321
Max Act: 0.6726. Min Act: -0.0001
Data Index: 479825 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19