Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 905 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1516. Min Act: -0.0001

Data Index: 224544 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1478. Min Act: -0.0001

Data Index: 533950 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1312. Min Act: -0.0001

Data Index: 1149072 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1290. Min Act: -0.0000

Data Index: 282076 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1309. Min Act: -0.0000

Data Index: 99179 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1196. Min Act: -0.0000

Data Index: 366113 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1172. Min Act: -0.0001

Data Index: 1217227 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1188. Min Act: -0.0000

Data Index: 1064026 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1136. Min Act: -0.0001

Data Index: 167432 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1223. Min Act: -0.0001

Data Index: 13165 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1174. Min Act: -0.0000

Data Index: 1142662 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1164. Min Act: -0.0000

Data Index: 1037720 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1160. Min Act: -0.0000

Data Index: 9949 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1162. Min Act: -0.0000

Data Index: 373187 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1142. Min Act: -0.0001

Data Index: 295135 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1078. Min Act: -0.0000

Data Index: 897859 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1127. Min Act: -0.0000

Data Index: 23313 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1080. Min Act: -0.0001

Data Index: 1249204 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1161. Min Act: -0.0000

Data Index: 356072 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1103. Min Act: -0.0001

Data Index: 1338021 (C4 (Web Text))

Max Activating Token Index: 410