Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4571 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.5763. Min Range: -2.5763
Max Act: 2.5763. Min Act: -0.0001
Data Index: 354045 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5763. Min Range: -2.5763
Max Act: 2.0230. Min Act: -0.0001
Data Index: 485980 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5763. Min Range: -2.5763
Max Act: 2.0731. Min Act: -0.0001
Data Index: 995102 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5763. Min Range: -2.5763
Max Act: 2.1171. Min Act: -0.0001
Data Index: 660743 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5763. Min Range: -2.5763
Max Act: 2.0114. Min Act: -0.0001
Data Index: 835528 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5763. Min Range: -2.5763
Max Act: 1.9480. Min Act: -0.0001
Data Index: 1622678 (Python Code)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5763. Min Range: -2.5763
Max Act: 1.9054. Min Act: -0.0001
Data Index: 226232 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5763. Min Range: -2.5763
Max Act: 1.9641. Min Act: -0.0001
Data Index: 916829 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5763. Min Range: -2.5763
Max Act: 1.9154. Min Act: -0.0001
Data Index: 1210886 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5763. Min Range: -2.5763
Max Act: 1.8019. Min Act: -0.0001
Data Index: 479336 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5763. Min Range: -2.5763
Max Act: 1.8791. Min Act: -0.0001
Data Index: 801460 (C4 (Web Text))
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5763. Min Range: -2.5763
Max Act: 1.8298. Min Act: -0.0001
Data Index: 366306 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5763. Min Range: -2.5763
Max Act: 1.9114. Min Act: -0.0001
Data Index: 216001 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5763. Min Range: -2.5763
Max Act: 1.8108. Min Act: -0.0001
Data Index: 894434 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5763. Min Range: -2.5763
Max Act: 1.7406. Min Act: -0.0001
Data Index: 611901 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5763. Min Range: -2.5763
Max Act: 1.8684. Min Act: -0.0001
Data Index: 484225 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5763. Min Range: -2.5763
Max Act: 1.8320. Min Act: -0.0001
Data Index: 336044 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5763. Min Range: -2.5763
Max Act: 1.8791. Min Act: -0.0001
Data Index: 363000 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5763. Min Range: -2.5763
Max Act: 1.8193. Min Act: -0.0001
Data Index: 394100 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5763. Min Range: -2.5763
Max Act: 1.8297. Min Act: -0.0001
Data Index: 1525551 (Python Code)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19