Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1900 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.8859. Min Range: -1.8859
Max Act: 1.8859. Min Act: -0.0001
Data Index: 1262057 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8859. Min Range: -1.8859
Max Act: 1.5355. Min Act: -0.0001
Data Index: 1126345 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8859. Min Range: -1.8859
Max Act: 1.3657. Min Act: -0.0001
Data Index: 133317 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8859. Min Range: -1.8859
Max Act: 1.3542. Min Act: -0.0001
Data Index: 300071 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8859. Min Range: -1.8859
Max Act: 1.1904. Min Act: -0.0001
Data Index: 607193 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8859. Min Range: -1.8859
Max Act: 1.2610. Min Act: -0.0001
Data Index: 1188759 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8859. Min Range: -1.8859
Max Act: 1.2822. Min Act: -0.0001
Data Index: 340000 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8859. Min Range: -1.8859
Max Act: 1.2912. Min Act: -0.0001
Data Index: 965292 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8859. Min Range: -1.8859
Max Act: 1.2482. Min Act: -0.0001
Data Index: 120465 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8859. Min Range: -1.8859
Max Act: 1.3558. Min Act: -0.0001
Data Index: 673677 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8859. Min Range: -1.8859
Max Act: 1.3476. Min Act: -0.0001
Data Index: 322836 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8859. Min Range: -1.8859
Max Act: 1.3648. Min Act: -0.0001
Data Index: 209598 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8859. Min Range: -1.8859
Max Act: 1.1994. Min Act: -0.0001
Data Index: 529217 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8859. Min Range: -1.8859
Max Act: 1.2700. Min Act: -0.0001
Data Index: 1303838 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8859. Min Range: -1.8859
Max Act: 1.1975. Min Act: -0.0001
Data Index: 866739 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8859. Min Range: -1.8859
Max Act: 1.2725. Min Act: -0.0001
Data Index: 1182819 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8859. Min Range: -1.8859
Max Act: 1.2243. Min Act: -0.0001
Data Index: 513525 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8859. Min Range: -1.8859
Max Act: 1.3054. Min Act: -0.0001
Data Index: 582482 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8859. Min Range: -1.8859
Max Act: 1.2917. Min Act: -0.0001
Data Index: 372409 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8859. Min Range: -1.8859
Max Act: 1.1147. Min Act: -0.0001
Data Index: 10839 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19