Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5007 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.6198. Min Act: -0.0000

Data Index: 134332 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.5843. Min Act: -0.0000

Data Index: 157108 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.5652. Min Act: -0.0000

Data Index: 1210908 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.5336. Min Act: -0.0000

Data Index: 431424 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.5166. Min Act: -0.0000

Data Index: 1033129 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4792. Min Act: -0.0000

Data Index: 824961 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4712. Min Act: -0.0000

Data Index: 609099 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.3957. Min Act: 0.0000

Data Index: 337211 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.3900. Min Act: -0.0000

Data Index: 984078 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.3811. Min Act: -0.0000

Data Index: 778237 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.3766. Min Act: -0.0000

Data Index: 421281 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.3302. Min Act: -0.0000

Data Index: 518331 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.3608. Min Act: -0.0000

Data Index: 903782 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.3594. Min Act: -0.0000

Data Index: 474562 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.3367. Min Act: -0.0000

Data Index: 634670 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.3203. Min Act: -0.0000

Data Index: 176182 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.3055. Min Act: -0.0000

Data Index: 294144 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.2978. Min Act: -0.0000

Data Index: 1005758 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.2881. Min Act: -0.0000

Data Index: 501489 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.2794. Min Act: -0.0000

Data Index: 6283 (C4 (Web Text))

Max Activating Token Index: 850