Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 100 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.0755. Min Range: -0.0755
Max Act: 0.0662. Min Act: -0.0001
Data Index: 210461 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0755. Min Range: -0.0755
Max Act: 0.0727. Min Act: -0.0001
Data Index: 382000 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0755. Min Range: -0.0755
Max Act: 0.0735. Min Act: -0.0001
Data Index: 1165390 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0755. Min Range: -0.0755
Max Act: 0.0683. Min Act: -0.0001
Data Index: 301260 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0755. Min Range: -0.0755
Max Act: 0.0755. Min Act: -0.0001
Data Index: 648739 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0755. Min Range: -0.0755
Max Act: 0.0678. Min Act: -0.0001
Data Index: 324378 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0755. Min Range: -0.0755
Max Act: 0.0719. Min Act: -0.0001
Data Index: 128494 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0755. Min Range: -0.0755
Max Act: 0.0621. Min Act: -0.0001
Data Index: 1525655 (Python Code)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0755. Min Range: -0.0755
Max Act: 0.0681. Min Act: -0.0001
Data Index: 310390 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0755. Min Range: -0.0755
Max Act: 0.0545. Min Act: -0.0001
Data Index: 692713 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0755. Min Range: -0.0755
Max Act: 0.0648. Min Act: -0.0001
Data Index: 1175946 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0755. Min Range: -0.0755
Max Act: 0.0491. Min Act: -0.0001
Data Index: 482654 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0755. Min Range: -0.0755
Max Act: 0.0545. Min Act: -0.0001
Data Index: 33129 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0755. Min Range: -0.0755
Max Act: 0.0526. Min Act: -0.0001
Data Index: 1178261 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0755. Min Range: -0.0755
Max Act: 0.0582. Min Act: -0.0001
Data Index: 226293 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0755. Min Range: -0.0755
Max Act: 0.0521. Min Act: -0.0001
Data Index: 507297 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0755. Min Range: -0.0755
Max Act: 0.0608. Min Act: -0.0001
Data Index: 903112 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0755. Min Range: -0.0755
Max Act: 0.0457. Min Act: -0.0001
Data Index: 1524378 (Python Code)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0755. Min Range: -0.0755
Max Act: 0.0512. Min Act: -0.0002
Data Index: 321838 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0755. Min Range: -0.0755
Max Act: 0.0508. Min Act: -0.0001
Data Index: 81570 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19