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

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

Neuron 3360 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: 0.1488. Min Range: -0.1488

Max Act: 0.1461. Min Act: -0.0000

Data Index: 613304 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1397. Min Act: -0.0001

Data Index: 1607765 (Python Code)

Max Activating Token Index: 927

Text #2

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1488. Min Act: -0.0000

Data Index: 1081770 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1272. Min Act: -0.0001

Data Index: 530732 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1365. Min Act: -0.0001

Data Index: 1422994 (Python Code)

Max Activating Token Index: 747

Text #5

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1405. Min Act: -0.0000

Data Index: 340407 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1291. Min Act: -0.0000

Data Index: 816541 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1305. Min Act: -0.0001

Data Index: 260738 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1276. Min Act: -0.0001

Data Index: 39999 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1322. Min Act: -0.0000

Data Index: 846898 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1318. Min Act: -0.0001

Data Index: 1301874 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1290. Min Act: -0.0001

Data Index: 235148 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1296. Min Act: -0.0000

Data Index: 1039946 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1241. Min Act: -0.0000

Data Index: 930834 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1271. Min Act: -0.0000

Data Index: 58099 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1238. Min Act: -0.0001

Data Index: 460220 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1212. Min Act: -0.0001

Data Index: 728975 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1165. Min Act: -0.0000

Data Index: 905455 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1245. Min Act: -0.0001

Data Index: 210177 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1196. Min Act: -0.0000

Data Index: 1198080 (C4 (Web Text))

Max Activating Token Index: 70