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

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

Neuron 1193 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1403. Min Act: -0.0001

Data Index: 430948 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1574. Min Act: -0.0001

Data Index: 833685 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1332. Min Act: -0.0001

Data Index: 1181754 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1364. Min Act: -0.0001

Data Index: 1193811 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1213. Min Act: -0.0001

Data Index: 117751 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1322. Min Act: -0.0001

Data Index: 884236 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1255. Min Act: -0.0001

Data Index: 670207 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1339. Min Act: -0.0001

Data Index: 287135 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1178. Min Act: -0.0001

Data Index: 984372 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1055. Min Act: -0.0001

Data Index: 82479 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1262. Min Act: -0.0001

Data Index: 957479 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1410. Min Act: -0.0001

Data Index: 614459 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1243. Min Act: -0.0001

Data Index: 1158149 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1242. Min Act: -0.0001

Data Index: 7247 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1316. Min Act: -0.0001

Data Index: 870529 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1277. Min Act: -0.0001

Data Index: 1310036 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1243. Min Act: -0.0001

Data Index: 1088061 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1174. Min Act: -0.0001

Data Index: 1062326 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1074. Min Act: -0.0001

Data Index: 313332 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1208. Min Act: -0.0001

Data Index: 985182 (C4 (Web Text))

Max Activating Token Index: 95