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

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

Neuron 2275 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: 0.1538. Min Range: -0.1538

Max Act: 0.1431. Min Act: -0.0001

Data Index: 1294644 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1538. Min Act: -0.0001

Data Index: 1272103 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1295. Min Act: -0.0000

Data Index: 626266 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1188. Min Act: -0.0001

Data Index: 1281962 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1223. Min Act: -0.0001

Data Index: 1397820 (Python Code)

Max Activating Token Index: 60

Text #5

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1252. Min Act: -0.0001

Data Index: 95097 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1186. Min Act: -0.0001

Data Index: 1300080 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1111. Min Act: -0.0001

Data Index: 941192 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1147. Min Act: -0.0001

Data Index: 1270231 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1162. Min Act: -0.0001

Data Index: 1216976 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1164. Min Act: -0.0001

Data Index: 411989 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1120. Min Act: -0.0001

Data Index: 790572 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1150. Min Act: -0.0001

Data Index: 432518 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1190. Min Act: -0.0001

Data Index: 1525702 (Python Code)

Max Activating Token Index: 139

Text #14

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1179. Min Act: -0.0001

Data Index: 1135719 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1105. Min Act: -0.0001

Data Index: 518053 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1135. Min Act: -0.0001

Data Index: 40979 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1131. Min Act: -0.0001

Data Index: 452348 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1128. Min Act: -0.0001

Data Index: 435373 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1115. Min Act: -0.0001

Data Index: 960219 (C4 (Web Text))

Max Activating Token Index: 445