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

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

Neuron 5188 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8221. Min Range: -2.8221

Max Act: 2.7291. Min Act: -0.0000

Data Index: 1342109 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 2.8221. Min Range: -2.8221

Max Act: 2.8221. Min Act: -0.0000

Data Index: 853264 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 2.8221. Min Range: -2.8221

Max Act: 2.5173. Min Act: -0.0000

Data Index: 116158 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 2.8221. Min Range: -2.8221

Max Act: 2.6927. Min Act: -0.0000

Data Index: 930751 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 2.8221. Min Range: -2.8221

Max Act: 2.5508. Min Act: -0.0000

Data Index: 354901 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 2.8221. Min Range: -2.8221

Max Act: 2.5527. Min Act: -0.0000

Data Index: 672653 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 2.8221. Min Range: -2.8221

Max Act: 2.4109. Min Act: -0.0000

Data Index: 552438 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 2.8221. Min Range: -2.8221

Max Act: 2.0837. Min Act: -0.0000

Data Index: 2093 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 2.8221. Min Range: -2.8221

Max Act: 2.5204. Min Act: -0.0000

Data Index: 1284989 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 2.8221. Min Range: -2.8221

Max Act: 2.2078. Min Act: -0.0000

Data Index: 209036 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 2.8221. Min Range: -2.8221

Max Act: 2.1028. Min Act: -0.0000

Data Index: 1260689 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 2.8221. Min Range: -2.8221

Max Act: 2.1722. Min Act: -0.0000

Data Index: 841473 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 2.8221. Min Range: -2.8221

Max Act: 2.4395. Min Act: -0.0000

Data Index: 1334710 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 2.8221. Min Range: -2.8221

Max Act: 2.1132. Min Act: -0.0000

Data Index: 1085898 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 2.8221. Min Range: -2.8221

Max Act: 2.0939. Min Act: -0.0000

Data Index: 1009035 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 2.8221. Min Range: -2.8221

Max Act: 2.1334. Min Act: -0.0000

Data Index: 1163010 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 2.8221. Min Range: -2.8221

Max Act: 2.1645. Min Act: -0.0000

Data Index: 377018 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 2.8221. Min Range: -2.8221

Max Act: 2.2980. Min Act: -0.0000

Data Index: 1254562 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 2.8221. Min Range: -2.8221

Max Act: 2.0290. Min Act: -0.0000

Data Index: 768424 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 2.8221. Min Range: -2.8221

Max Act: 1.9594. Min Act: -0.0000

Data Index: 467667 (C4 (Web Text))

Max Activating Token Index: 734