Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1360 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 6.1337. Min Range: -6.1337
Max Act: 6.1337. Min Act: -0.0001
Data Index: 44448 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1337. Min Range: -6.1337
Max Act: 5.9150. Min Act: -0.0001
Data Index: 1130984 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1337. Min Range: -6.1337
Max Act: 5.7799. Min Act: -0.0001
Data Index: 185212 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1337. Min Range: -6.1337
Max Act: 5.7780. Min Act: -0.0001
Data Index: 350501 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1337. Min Range: -6.1337
Max Act: 5.3370. Min Act: -0.0001
Data Index: 646068 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1337. Min Range: -6.1337
Max Act: 5.4033. Min Act: -0.0001
Data Index: 28644 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1337. Min Range: -6.1337
Max Act: 5.0559. Min Act: -0.0001
Data Index: 228579 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1337. Min Range: -6.1337
Max Act: 5.3354. Min Act: -0.0001
Data Index: 1180447 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1337. Min Range: -6.1337
Max Act: 4.9114. Min Act: -0.0001
Data Index: 564766 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1337. Min Range: -6.1337
Max Act: 5.4229. Min Act: -0.0001
Data Index: 744513 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1337. Min Range: -6.1337
Max Act: 5.5805. Min Act: -0.0001
Data Index: 678538 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1337. Min Range: -6.1337
Max Act: 5.3523. Min Act: -0.0001
Data Index: 201093 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1337. Min Range: -6.1337
Max Act: 5.3989. Min Act: -0.0001
Data Index: 1275477 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1337. Min Range: -6.1337
Max Act: 5.3941. Min Act: -0.0001
Data Index: 1027326 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1337. Min Range: -6.1337
Max Act: 4.8518. Min Act: -0.0001
Data Index: 602439 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1337. Min Range: -6.1337
Max Act: 5.1526. Min Act: -0.0001
Data Index: 936166 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1337. Min Range: -6.1337
Max Act: 5.1558. Min Act: -0.0001
Data Index: 1004797 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1337. Min Range: -6.1337
Max Act: 5.1459. Min Act: -0.0001
Data Index: 943836 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1337. Min Range: -6.1337
Max Act: 4.6069. Min Act: -0.0001
Data Index: 596118 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1337. Min Range: -6.1337
Max Act: 4.8869. Min Act: -0.0001
Data Index: 572339 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19