Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2907 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 3.2054. Min Range: -3.2054
Max Act: 3.2054. Min Act: -0.0001
Data Index: 972475 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2054. Min Range: -3.2054
Max Act: 2.8198. Min Act: -0.0001
Data Index: 5715 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2054. Min Range: -3.2054
Max Act: 2.6821. Min Act: -0.0001
Data Index: 1280517 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2054. Min Range: -3.2054
Max Act: 2.4636. Min Act: -0.0001
Data Index: 963526 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2054. Min Range: -3.2054
Max Act: 2.5910. Min Act: -0.0001
Data Index: 108126 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2054. Min Range: -3.2054
Max Act: 2.4647. Min Act: -0.0001
Data Index: 89510 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2054. Min Range: -3.2054
Max Act: 2.7254. Min Act: -0.0001
Data Index: 1222350 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2054. Min Range: -3.2054
Max Act: 2.4031. Min Act: -0.0001
Data Index: 166805 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2054. Min Range: -3.2054
Max Act: 2.3949. Min Act: -0.0001
Data Index: 3278 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2054. Min Range: -3.2054
Max Act: 2.3788. Min Act: -0.0001
Data Index: 235993 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2054. Min Range: -3.2054
Max Act: 2.6039. Min Act: -0.0001
Data Index: 890801 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2054. Min Range: -3.2054
Max Act: 2.3836. Min Act: -0.0001
Data Index: 1275944 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2054. Min Range: -3.2054
Max Act: 2.3976. Min Act: -0.0001
Data Index: 925541 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2054. Min Range: -3.2054
Max Act: 2.2762. Min Act: -0.0001
Data Index: 174315 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2054. Min Range: -3.2054
Max Act: 2.4344. Min Act: -0.0001
Data Index: 1329930 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2054. Min Range: -3.2054
Max Act: 2.2798. Min Act: -0.0001
Data Index: 192469 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2054. Min Range: -3.2054
Max Act: 2.2664. Min Act: -0.0001
Data Index: 605276 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2054. Min Range: -3.2054
Max Act: 2.1119. Min Act: -0.0001
Data Index: 76673 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2054. Min Range: -3.2054
Max Act: 2.2431. Min Act: -0.0001
Data Index: 1211770 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2054. Min Range: -3.2054
Max Act: 2.4912. Min Act: -0.0001
Data Index: 378643 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19