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

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

Neuron 1161 in Layer 0

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: 0.1423. Min Range: -0.1423

Max Act: 0.1410. Min Act: -0.0001

Data Index: 40544 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1423. Min Act: -0.0001

Data Index: 1024940 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1370. Min Act: -0.0001

Data Index: 1248713 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1336. Min Act: -0.0001

Data Index: 144378 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1324. Min Act: -0.0001

Data Index: 64181 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1282. Min Act: -0.0001

Data Index: 491772 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1270. Min Act: -0.0001

Data Index: 118961 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1262. Min Act: -0.0001

Data Index: 1129282 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1257. Min Act: -0.0001

Data Index: 43020 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1238. Min Act: -0.0001

Data Index: 224272 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1229. Min Act: -0.0001

Data Index: 1043742 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1216. Min Act: -0.0001

Data Index: 1268135 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1214. Min Act: -0.0001

Data Index: 76972 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1201. Min Act: -0.0001

Data Index: 546630 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1214. Min Act: -0.0001

Data Index: 430407 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1171. Min Act: -0.0001

Data Index: 55522 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1145. Min Act: -0.0001

Data Index: 1265861 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1150. Min Act: -0.0001

Data Index: 493430 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1129. Min Act: -0.0001

Data Index: 139220 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1136. Min Act: -0.0001

Data Index: 455180 (C4 (Web Text))

Max Activating Token Index: 44