Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2262 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.9733. Min Range: -1.9733
Max Act: 1.9345. Min Act: -0.0001
Data Index: 318647 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9733. Min Range: -1.9733
Max Act: 1.8804. Min Act: -0.0001
Data Index: 754600 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9733. Min Range: -1.9733
Max Act: 1.9733. Min Act: -0.0001
Data Index: 1143975 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9733. Min Range: -1.9733
Max Act: 1.9587. Min Act: -0.0001
Data Index: 799697 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9733. Min Range: -1.9733
Max Act: 1.8447. Min Act: -0.0001
Data Index: 1575734 (Python Code)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9733. Min Range: -1.9733
Max Act: 1.8950. Min Act: -0.0001
Data Index: 1155606 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9733. Min Range: -1.9733
Max Act: 1.7965. Min Act: -0.0001
Data Index: 281524 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9733. Min Range: -1.9733
Max Act: 1.7023. Min Act: -0.0001
Data Index: 597457 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9733. Min Range: -1.9733
Max Act: 1.6961. Min Act: -0.0001
Data Index: 1529784 (Python Code)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9733. Min Range: -1.9733
Max Act: 1.6229. Min Act: -0.0001
Data Index: 412873 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9733. Min Range: -1.9733
Max Act: 1.5693. Min Act: -0.0001
Data Index: 1209371 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9733. Min Range: -1.9733
Max Act: 1.5106. Min Act: -0.0001
Data Index: 804161 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9733. Min Range: -1.9733
Max Act: 1.4894. Min Act: -0.0001
Data Index: 402693 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9733. Min Range: -1.9733
Max Act: 1.5112. Min Act: -0.0001
Data Index: 132657 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9733. Min Range: -1.9733
Max Act: 1.4530. Min Act: -0.0001
Data Index: 1325424 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9733. Min Range: -1.9733
Max Act: 1.5199. Min Act: -0.0001
Data Index: 451128 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9733. Min Range: -1.9733
Max Act: 1.4737. Min Act: -0.0001
Data Index: 39066 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9733. Min Range: -1.9733
Max Act: 1.5849. Min Act: -0.0001
Data Index: 1558329 (Python Code)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9733. Min Range: -1.9733
Max Act: 1.5006. Min Act: -0.0001
Data Index: 1159582 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9733. Min Range: -1.9733
Max Act: 1.4553. Min Act: -0.0001
Data Index: 420769 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19