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

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

Neuron 1948 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: 2.4112. Min Range: -2.4112

Max Act: 2.3990. Min Act: -0.0000

Data Index: 887176 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 2.4112. Min Range: -2.4112

Max Act: 2.3245. Min Act: -0.0000

Data Index: 92698 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 2.4112. Min Range: -2.4112

Max Act: 2.4112. Min Act: -0.0000

Data Index: 775524 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 2.4112. Min Range: -2.4112

Max Act: 2.2693. Min Act: -0.0000

Data Index: 1031557 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 2.4112. Min Range: -2.4112

Max Act: 2.3552. Min Act: -0.0000

Data Index: 560940 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 2.4112. Min Range: -2.4112

Max Act: 2.2612. Min Act: -0.0000

Data Index: 601874 (C4 (Web Text))

Max Activating Token Index: 580

Text #6

Max Range: 2.4112. Min Range: -2.4112

Max Act: 2.4066. Min Act: -0.0000

Data Index: 139585 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 2.4112. Min Range: -2.4112

Max Act: 2.2690. Min Act: -0.0000

Data Index: 655913 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 2.4112. Min Range: -2.4112

Max Act: 2.2338. Min Act: -0.0000

Data Index: 529352 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 2.4112. Min Range: -2.4112

Max Act: 2.2093. Min Act: -0.0000

Data Index: 1304044 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 2.4112. Min Range: -2.4112

Max Act: 2.3414. Min Act: -0.0000

Data Index: 294107 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 2.4112. Min Range: -2.4112

Max Act: 2.2035. Min Act: -0.0000

Data Index: 1270159 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 2.4112. Min Range: -2.4112

Max Act: 2.1020. Min Act: -0.0000

Data Index: 28404 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 2.4112. Min Range: -2.4112

Max Act: 2.1589. Min Act: -0.0000

Data Index: 1061314 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 2.4112. Min Range: -2.4112

Max Act: 2.2596. Min Act: -0.0000

Data Index: 825925 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 2.4112. Min Range: -2.4112

Max Act: 2.0994. Min Act: -0.0000

Data Index: 846021 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 2.4112. Min Range: -2.4112

Max Act: 2.0591. Min Act: -0.0000

Data Index: 52998 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 2.4112. Min Range: -2.4112

Max Act: 2.0275. Min Act: -0.0000

Data Index: 506483 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 2.4112. Min Range: -2.4112

Max Act: 1.9831. Min Act: -0.0000

Data Index: 1347452 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 2.4112. Min Range: -2.4112

Max Act: 1.9918. Min Act: -0.0000

Data Index: 229615 (C4 (Web Text))

Max Activating Token Index: 64