Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2878 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.3590. Min Range: -2.3590
Max Act: 2.3590. Min Act: -0.0001
Data Index: 417863 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3590. Min Range: -2.3590
Max Act: 2.0693. Min Act: -0.0001
Data Index: 65284 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3590. Min Range: -2.3590
Max Act: 2.0719. Min Act: -0.0001
Data Index: 438517 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3590. Min Range: -2.3590
Max Act: 2.1631. Min Act: -0.0001
Data Index: 1077318 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3590. Min Range: -2.3590
Max Act: 2.2077. Min Act: -0.0001
Data Index: 392077 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3590. Min Range: -2.3590
Max Act: 1.8390. Min Act: -0.0001
Data Index: 785681 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3590. Min Range: -2.3590
Max Act: 2.0505. Min Act: -0.0001
Data Index: 239878 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3590. Min Range: -2.3590
Max Act: 1.7200. Min Act: -0.0001
Data Index: 51788 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3590. Min Range: -2.3590
Max Act: 1.9107. Min Act: -0.0001
Data Index: 367020 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3590. Min Range: -2.3590
Max Act: 1.6926. Min Act: -0.0001
Data Index: 381413 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3590. Min Range: -2.3590
Max Act: 1.5564. Min Act: -0.0001
Data Index: 1066939 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3590. Min Range: -2.3590
Max Act: 1.4580. Min Act: -0.0001
Data Index: 231613 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3590. Min Range: -2.3590
Max Act: 1.3705. Min Act: -0.0000
Data Index: 1564410 (Python Code)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3590. Min Range: -2.3590
Max Act: 1.5383. Min Act: -0.0001
Data Index: 41538 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3590. Min Range: -2.3590
Max Act: 1.5239. Min Act: -0.0001
Data Index: 804018 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3590. Min Range: -2.3590
Max Act: 1.5043. Min Act: -0.0001
Data Index: 1203066 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3590. Min Range: -2.3590
Max Act: 1.3655. Min Act: -0.0001
Data Index: 515499 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3590. Min Range: -2.3590
Max Act: 1.3740. Min Act: -0.0001
Data Index: 1196406 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3590. Min Range: -2.3590
Max Act: 1.2112. Min Act: -0.0001
Data Index: 1179835 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3590. Min Range: -2.3590
Max Act: 1.2080. Min Act: -0.0001
Data Index: 833520 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19