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

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

Neuron 2838 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: 0.1826. Min Range: -0.1826

Max Act: 0.1826. Min Act: -0.0000

Data Index: 384169 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1677. Min Act: -0.0001

Data Index: 48135 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1510. Min Act: -0.0001

Data Index: 271945 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1493. Min Act: -0.0001

Data Index: 929126 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1474. Min Act: -0.0001

Data Index: 1146342 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1491. Min Act: -0.0001

Data Index: 1300980 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1429. Min Act: -0.0001

Data Index: 824444 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1431. Min Act: -0.0000

Data Index: 1121928 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1335. Min Act: -0.0001

Data Index: 27390 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1306. Min Act: -0.0001

Data Index: 726330 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1238. Min Act: -0.0001

Data Index: 667590 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1230. Min Act: -0.0000

Data Index: 883018 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1216. Min Act: -0.0001

Data Index: 1357036 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1287. Min Act: -0.0001

Data Index: 573640 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1198. Min Act: -0.0001

Data Index: 1225548 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1188. Min Act: -0.0000

Data Index: 548430 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1215. Min Act: -0.0000

Data Index: 199972 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1214. Min Act: -0.0001

Data Index: 949202 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1168. Min Act: -0.0000

Data Index: 866061 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1157. Min Act: -0.0000

Data Index: 1052520 (C4 (Web Text))

Max Activating Token Index: 766