Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 395 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1744. Min Act: -0.0001

Data Index: 1277029 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1529. Min Act: -0.0001

Data Index: 989364 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1285. Min Act: -0.0001

Data Index: 996728 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1218. Min Act: -0.0001

Data Index: 805023 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1230. Min Act: -0.0001

Data Index: 269836 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1206. Min Act: -0.0001

Data Index: 414155 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1174. Min Act: -0.0001

Data Index: 1031639 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1155. Min Act: -0.0001

Data Index: 1237702 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1235. Min Act: -0.0001

Data Index: 359357 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1216. Min Act: -0.0001

Data Index: 953967 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1167. Min Act: -0.0001

Data Index: 904924 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.0994. Min Act: -0.0001

Data Index: 116718 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1173. Min Act: -0.0001

Data Index: 770838 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1319. Min Act: -0.0001

Data Index: 1284386 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1176. Min Act: -0.0001

Data Index: 104777 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1135. Min Act: -0.0001

Data Index: 904307 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1026. Min Act: -0.0001

Data Index: 1012786 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1092. Min Act: -0.0001

Data Index: 245644 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1143. Min Act: -0.0001

Data Index: 526130 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1040. Min Act: -0.0001

Data Index: 470157 (C4 (Web Text))

Max Activating Token Index: 227