Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2405 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.5556. Min Range: -1.5556
Max Act: 1.5556. Min Act: -0.0001
Data Index: 410414 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5556. Min Range: -1.5556
Max Act: 1.5050. Min Act: -0.0001
Data Index: 361922 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5556. Min Range: -1.5556
Max Act: 1.4671. Min Act: -0.0001
Data Index: 1194174 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5556. Min Range: -1.5556
Max Act: 1.3471. Min Act: -0.0001
Data Index: 481472 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5556. Min Range: -1.5556
Max Act: 1.3789. Min Act: -0.0001
Data Index: 881188 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5556. Min Range: -1.5556
Max Act: 1.1523. Min Act: -0.0001
Data Index: 1511503 (Python Code)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5556. Min Range: -1.5556
Max Act: 1.2615. Min Act: -0.0001
Data Index: 753707 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5556. Min Range: -1.5556
Max Act: 1.3432. Min Act: -0.0001
Data Index: 701001 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5556. Min Range: -1.5556
Max Act: 1.2970. Min Act: -0.0001
Data Index: 209697 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5556. Min Range: -1.5556
Max Act: 1.2818. Min Act: -0.0001
Data Index: 1560376 (Python Code)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5556. Min Range: -1.5556
Max Act: 1.2327. Min Act: -0.0001
Data Index: 354402 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5556. Min Range: -1.5556
Max Act: 1.2112. Min Act: -0.0001
Data Index: 681233 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5556. Min Range: -1.5556
Max Act: 1.1862. Min Act: -0.0001
Data Index: 693502 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5556. Min Range: -1.5556
Max Act: 0.9724. Min Act: -0.0001
Data Index: 1112946 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5556. Min Range: -1.5556
Max Act: 1.2181. Min Act: -0.0001
Data Index: 835595 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5556. Min Range: -1.5556
Max Act: 1.1665. Min Act: -0.0001
Data Index: 304856 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5556. Min Range: -1.5556
Max Act: 1.0098. Min Act: -0.0001
Data Index: 146389 (C4 (Web Text))
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5556. Min Range: -1.5556
Max Act: 1.1129. Min Act: -0.0001
Data Index: 1284650 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5556. Min Range: -1.5556
Max Act: 1.1384. Min Act: -0.0001
Data Index: 313028 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5556. Min Range: -1.5556
Max Act: 1.0805. Min Act: -0.0001
Data Index: 62095 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19