Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4412 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1395. Min Act: -0.0001

Data Index: 677495 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1277. Min Act: -0.0001

Data Index: 301822 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1389. Min Act: -0.0001

Data Index: 1159674 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1173. Min Act: -0.0001

Data Index: 1042889 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1192. Min Act: -0.0001

Data Index: 514413 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1225. Min Act: -0.0001

Data Index: 504647 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1081. Min Act: -0.0001

Data Index: 149464 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1129. Min Act: -0.0001

Data Index: 747932 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1060. Min Act: -0.0001

Data Index: 270035 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1158. Min Act: -0.0001

Data Index: 83760 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1200. Min Act: -0.0001

Data Index: 201195 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1191. Min Act: -0.0001

Data Index: 824978 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1098. Min Act: -0.0001

Data Index: 543517 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1242. Min Act: -0.0001

Data Index: 722146 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1188. Min Act: -0.0001

Data Index: 874750 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1177. Min Act: -0.0001

Data Index: 480634 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1001. Min Act: -0.0001

Data Index: 634502 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1082. Min Act: -0.0001

Data Index: 1283334 (C4 (Web Text))

Max Activating Token Index: 70

Text #18

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1185. Min Act: -0.0001

Data Index: 1047021 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1105. Min Act: -0.0001

Data Index: 850064 (C4 (Web Text))

Max Activating Token Index: 83