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

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

Neuron 2626 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: 0.2909. Min Range: -0.2909

Max Act: 0.2909. Min Act: -0.0001

Data Index: 956894 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2680. Min Act: -0.0001

Data Index: 1041405 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2351. Min Act: -0.0001

Data Index: 92553 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2404. Min Act: -0.0001

Data Index: 253509 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2319. Min Act: -0.0001

Data Index: 1180002 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2333. Min Act: -0.0001

Data Index: 947930 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2107. Min Act: -0.0001

Data Index: 104628 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2502. Min Act: -0.0001

Data Index: 286469 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2245. Min Act: -0.0001

Data Index: 1064418 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2175. Min Act: -0.0001

Data Index: 602888 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2015. Min Act: -0.0001

Data Index: 1127566 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2087. Min Act: -0.0001

Data Index: 455954 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2022. Min Act: -0.0001

Data Index: 386087 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.1907. Min Act: -0.0001

Data Index: 561290 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2141. Min Act: -0.0001

Data Index: 1310394 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.1858. Min Act: -0.0001

Data Index: 595448 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2023. Min Act: -0.0001

Data Index: 925628 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.1967. Min Act: -0.0001

Data Index: 682478 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2084. Min Act: -0.0001

Data Index: 180137 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2036. Min Act: -0.0001

Data Index: 755143 (C4 (Web Text))

Max Activating Token Index: 776