Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3038 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.3086. Min Range: -0.3086
Max Act: 0.3086. Min Act: -0.0001
Data Index: 9663 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.3086. Min Range: -0.3086
Max Act: 0.2976. Min Act: -0.0001
Data Index: 124761 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.3086. Min Range: -0.3086
Max Act: 0.2841. Min Act: -0.0001
Data Index: 668151 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.3086. Min Range: -0.3086
Max Act: 0.2773. Min Act: -0.0001
Data Index: 501362 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.3086. Min Range: -0.3086
Max Act: 0.2683. Min Act: -0.0001
Data Index: 77756 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.3086. Min Range: -0.3086
Max Act: 0.2797. Min Act: -0.0001
Data Index: 646650 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.3086. Min Range: -0.3086
Max Act: 0.2818. Min Act: -0.0001
Data Index: 836867 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.3086. Min Range: -0.3086
Max Act: 0.2834. Min Act: -0.0001
Data Index: 404881 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.3086. Min Range: -0.3086
Max Act: 0.2657. Min Act: -0.0001
Data Index: 1006303 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.3086. Min Range: -0.3086
Max Act: 0.2616. Min Act: -0.0001
Data Index: 129816 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.3086. Min Range: -0.3086
Max Act: 0.2588. Min Act: -0.0001
Data Index: 664845 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.3086. Min Range: -0.3086
Max Act: 0.2611. Min Act: -0.0001
Data Index: 1096692 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.3086. Min Range: -0.3086
Max Act: 0.2675. Min Act: -0.0001
Data Index: 463513 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.3086. Min Range: -0.3086
Max Act: 0.2508. Min Act: -0.0001
Data Index: 613185 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.3086. Min Range: -0.3086
Max Act: 0.2562. Min Act: -0.0001
Data Index: 1050002 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.3086. Min Range: -0.3086
Max Act: 0.2469. Min Act: -0.0001
Data Index: 619536 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.3086. Min Range: -0.3086
Max Act: 0.2518. Min Act: -0.0001
Data Index: 43761 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.3086. Min Range: -0.3086
Max Act: 0.2601. Min Act: -0.0001
Data Index: 1234306 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.3086. Min Range: -0.3086
Max Act: 0.2335. Min Act: -0.0001
Data Index: 703404 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.3086. Min Range: -0.3086
Max Act: 0.2613. Min Act: -0.0001
Data Index: 100407 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19