Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1269 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0866. Min Range: -1.0866

Max Act: 1.0866. Min Act: -0.0001

Data Index: 626443 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.8960. Min Act: -0.0001

Data Index: 106385 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.8913. Min Act: -0.0001

Data Index: 371167 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.8657. Min Act: -0.0001

Data Index: 1305270 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.7967. Min Act: -0.0001

Data Index: 699413 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.8878. Min Act: -0.0001

Data Index: 628292 (C4 (Web Text))

Max Activating Token Index: 542

Text #6

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.8350. Min Act: -0.0001

Data Index: 289180 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.8239. Min Act: -0.0001

Data Index: 191133 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.7703. Min Act: -0.0001

Data Index: 75434 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.7890. Min Act: -0.0001

Data Index: 877532 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.7902. Min Act: -0.0001

Data Index: 888005 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.7535. Min Act: -0.0001

Data Index: 1180106 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.7394. Min Act: -0.0001

Data Index: 930969 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.7918. Min Act: -0.0001

Data Index: 183803 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.6994. Min Act: -0.0001

Data Index: 1224123 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.6782. Min Act: -0.0001

Data Index: 1281884 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.8151. Min Act: -0.0001

Data Index: 730685 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.7165. Min Act: -0.0001

Data Index: 612726 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.7098. Min Act: -0.0001

Data Index: 754906 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.6219. Min Act: -0.0001

Data Index: 1331371 (C4 (Web Text))

Max Activating Token Index: 697