Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1417 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.4810. Min Act: -0.0000

Data Index: 1002947 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.4382. Min Act: 0.0000

Data Index: 1329026 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.4063. Min Act: -0.0000

Data Index: 807056 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.3805. Min Act: 0.0000

Data Index: 136809 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.3733. Min Act: -0.0000

Data Index: 920761 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.3508. Min Act: -0.0000

Data Index: 644975 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.3296. Min Act: -0.0000

Data Index: 425276 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.3041. Min Act: -0.0000

Data Index: 1234679 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2984. Min Act: -0.0000

Data Index: 739185 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2919. Min Act: 0.0000

Data Index: 999670 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2980. Min Act: -0.0000

Data Index: 1248753 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2985. Min Act: -0.0000

Data Index: 811834 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2952. Min Act: -0.0000

Data Index: 1189209 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2891. Min Act: -0.0000

Data Index: 343723 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2970. Min Act: -0.0000

Data Index: 58326 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2839. Min Act: -0.0000

Data Index: 699498 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2833. Min Act: -0.0000

Data Index: 833642 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2894. Min Act: -0.0000

Data Index: 812471 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2913. Min Act: -0.0000

Data Index: 1018415 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2890. Min Act: 0.0000

Data Index: 62431 (C4 (Web Text))

Max Activating Token Index: 129