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

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

Neuron 721 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0307. Min Range: -2.0307

Max Act: 2.0307. Min Act: -0.0000

Data Index: 746906 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 2.0307. Min Range: -2.0307

Max Act: 1.9590. Min Act: -0.0000

Data Index: 1035867 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 2.0307. Min Range: -2.0307

Max Act: 1.7034. Min Act: -0.0000

Data Index: 1202494 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 2.0307. Min Range: -2.0307

Max Act: 1.6212. Min Act: -0.0000

Data Index: 974524 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 2.0307. Min Range: -2.0307

Max Act: 1.7064. Min Act: -0.0000

Data Index: 490687 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 2.0307. Min Range: -2.0307

Max Act: 1.6943. Min Act: -0.0000

Data Index: 416864 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 2.0307. Min Range: -2.0307

Max Act: 1.6507. Min Act: -0.0000

Data Index: 147857 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 2.0307. Min Range: -2.0307

Max Act: 1.8472. Min Act: -0.0000

Data Index: 129659 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 2.0307. Min Range: -2.0307

Max Act: 1.6177. Min Act: -0.0000

Data Index: 1309710 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 2.0307. Min Range: -2.0307

Max Act: 1.5164. Min Act: -0.0000

Data Index: 1054119 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 2.0307. Min Range: -2.0307

Max Act: 1.4878. Min Act: -0.0000

Data Index: 786202 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 2.0307. Min Range: -2.0307

Max Act: 1.4851. Min Act: -0.0000

Data Index: 1294354 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 2.0307. Min Range: -2.0307

Max Act: 1.4234. Min Act: -0.0000

Data Index: 120321 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 2.0307. Min Range: -2.0307

Max Act: 1.4171. Min Act: -0.0000

Data Index: 15398 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 2.0307. Min Range: -2.0307

Max Act: 1.5039. Min Act: -0.0000

Data Index: 1304665 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 2.0307. Min Range: -2.0307

Max Act: 1.3387. Min Act: -0.0000

Data Index: 54590 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 2.0307. Min Range: -2.0307

Max Act: 1.4758. Min Act: -0.0000

Data Index: 1173535 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 2.0307. Min Range: -2.0307

Max Act: 1.4202. Min Act: -0.0000

Data Index: 1311352 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 2.0307. Min Range: -2.0307

Max Act: 1.3013. Min Act: -0.0000

Data Index: 1020737 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 2.0307. Min Range: -2.0307

Max Act: 1.3672. Min Act: -0.0000

Data Index: 225060 (C4 (Web Text))

Max Activating Token Index: 463