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

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

Neuron 1419 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1374. Min Act: -0.0000

Data Index: 1164842 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1238. Min Act: -0.0001

Data Index: 1358560 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1273. Min Act: -0.0000

Data Index: 992332 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1225. Min Act: -0.0001

Data Index: 824364 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1256. Min Act: -0.0000

Data Index: 286269 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1191. Min Act: -0.0000

Data Index: 296094 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1190. Min Act: -0.0000

Data Index: 423833 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1122. Min Act: -0.0001

Data Index: 603517 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1153. Min Act: -0.0000

Data Index: 1017570 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1147. Min Act: -0.0001

Data Index: 244216 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1144. Min Act: -0.0000

Data Index: 1239097 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1146. Min Act: -0.0000

Data Index: 891909 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1131. Min Act: -0.0000

Data Index: 241184 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1091. Min Act: -0.0000

Data Index: 391736 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1108. Min Act: -0.0000

Data Index: 1317894 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1132. Min Act: -0.0000

Data Index: 225252 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1120. Min Act: -0.0000

Data Index: 658720 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1080. Min Act: -0.0000

Data Index: 443237 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1119. Min Act: -0.0001

Data Index: 398119 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1078. Min Act: -0.0001

Data Index: 356346 (C4 (Web Text))

Max Activating Token Index: 616