Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3002 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1778. Min Act: -0.0001

Data Index: 353458 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1434. Min Act: -0.0001

Data Index: 143369 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1422. Min Act: -0.0001

Data Index: 425256 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1212. Min Act: -0.0001

Data Index: 1300063 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1218. Min Act: -0.0001

Data Index: 528282 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1257. Min Act: -0.0001

Data Index: 1131955 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1148. Min Act: -0.0001

Data Index: 145892 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1237. Min Act: -0.0001

Data Index: 1096141 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1227. Min Act: -0.0001

Data Index: 860647 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1130. Min Act: -0.0001

Data Index: 1208124 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1171. Min Act: -0.0001

Data Index: 1191783 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1159. Min Act: -0.0001

Data Index: 469693 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1165. Min Act: -0.0001

Data Index: 1342537 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1155. Min Act: -0.0001

Data Index: 560363 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1150. Min Act: -0.0001

Data Index: 337213 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1082. Min Act: -0.0001

Data Index: 450354 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1072. Min Act: -0.0001

Data Index: 1196644 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1095. Min Act: -0.0001

Data Index: 628142 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1094. Min Act: -0.0001

Data Index: 430412 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1094. Min Act: -0.0001

Data Index: 345342 (C4 (Web Text))

Max Activating Token Index: 534