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

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

Neuron 1290 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.4884. Min Act: -0.0000

Data Index: 150823 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.4403. Min Act: -0.0000

Data Index: 515563 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.4305. Min Act: -0.0000

Data Index: 1057135 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.4293. Min Act: -0.0000

Data Index: 1041663 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.3928. Min Act: -0.0000

Data Index: 1162900 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.3402. Min Act: -0.0000

Data Index: 271839 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.3373. Min Act: -0.0000

Data Index: 391028 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.3211. Min Act: -0.0000

Data Index: 535074 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.3292. Min Act: -0.0000

Data Index: 44546 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.2959. Min Act: -0.0000

Data Index: 287023 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.3020. Min Act: -0.0000

Data Index: 896580 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.3017. Min Act: -0.0000

Data Index: 627687 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.2843. Min Act: -0.0000

Data Index: 1258739 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.2798. Min Act: -0.0000

Data Index: 591285 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.2865. Min Act: -0.0000

Data Index: 601325 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.2654. Min Act: -0.0000

Data Index: 906944 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.2912. Min Act: -0.0000

Data Index: 549744 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.2817. Min Act: -0.0000

Data Index: 416690 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.2861. Min Act: -0.0000

Data Index: 55131 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.2825. Min Act: -0.0000

Data Index: 4397 (C4 (Web Text))

Max Activating Token Index: 921