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

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

Neuron 944 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2734. Min Act: -0.0000

Data Index: 656556 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2890. Min Act: -0.0000

Data Index: 226357 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2424. Min Act: -0.0000

Data Index: 38361 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2509. Min Act: -0.0000

Data Index: 1202728 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2371. Min Act: -0.0000

Data Index: 407507 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2543. Min Act: -0.0000

Data Index: 701235 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2447. Min Act: -0.0000

Data Index: 687560 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2417. Min Act: -0.0000

Data Index: 943458 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2183. Min Act: -0.0000

Data Index: 1184859 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2314. Min Act: -0.0000

Data Index: 225719 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2062. Min Act: -0.0000

Data Index: 352946 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2235. Min Act: -0.0000

Data Index: 936667 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2170. Min Act: -0.0000

Data Index: 1559566 (Python Code)

Max Activating Token Index: 721

Text #13

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2133. Min Act: -0.0000

Data Index: 1158681 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2103. Min Act: -0.0000

Data Index: 1342277 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1960. Min Act: -0.0000

Data Index: 224145 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1984. Min Act: -0.0000

Data Index: 58981 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2082. Min Act: -0.0000

Data Index: 1053127 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2015. Min Act: -0.0000

Data Index: 248381 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1943. Min Act: -0.0000

Data Index: 98963 (C4 (Web Text))

Max Activating Token Index: 735