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

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

Neuron 4240 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1348. Min Act: -0.0002

Data Index: 1053736 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1321. Min Act: -0.0002

Data Index: 581057 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1353. Min Act: -0.0002

Data Index: 1183052 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1321. Min Act: -0.0002

Data Index: 1226730 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1334. Min Act: -0.0003

Data Index: 1229034 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1294. Min Act: -0.0002

Data Index: 37205 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1327. Min Act: -0.0003

Data Index: 1193789 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1303. Min Act: -0.0002

Data Index: 723662 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1329. Min Act: -0.0002

Data Index: 98398 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1291. Min Act: -0.0002

Data Index: 789176 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1287. Min Act: -0.0002

Data Index: 181694 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1289. Min Act: -0.0002

Data Index: 823328 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1300. Min Act: -0.0002

Data Index: 995177 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1275. Min Act: -0.0003

Data Index: 1311225 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1286. Min Act: -0.0002

Data Index: 1286978 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1286. Min Act: -0.0002

Data Index: 67112 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1318. Min Act: -0.0002

Data Index: 355609 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1306. Min Act: -0.0002

Data Index: 402376 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1270. Min Act: -0.0002

Data Index: 1248323 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1288. Min Act: -0.0002

Data Index: 1302230 (C4 (Web Text))

Max Activating Token Index: 29