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

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

Neuron 608 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1892. Min Act: -0.0001

Data Index: 961853 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1382. Min Act: -0.0001

Data Index: 422975 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1352. Min Act: -0.0001

Data Index: 1121002 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1406. Min Act: -0.0001

Data Index: 192991 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1286. Min Act: -0.0001

Data Index: 942383 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1411. Min Act: -0.0001

Data Index: 922064 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1465. Min Act: -0.0001

Data Index: 318087 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1378. Min Act: -0.0001

Data Index: 620857 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1335. Min Act: -0.0001

Data Index: 877597 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1335. Min Act: -0.0001

Data Index: 412656 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1413. Min Act: -0.0001

Data Index: 269765 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1354. Min Act: -0.0001

Data Index: 399155 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1349. Min Act: -0.0001

Data Index: 719895 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1206. Min Act: -0.0001

Data Index: 108135 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1433. Min Act: -0.0001

Data Index: 1129062 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1248. Min Act: -0.0001

Data Index: 412165 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1316. Min Act: -0.0001

Data Index: 1201604 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1247. Min Act: -0.0001

Data Index: 35167 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1285. Min Act: -0.0001

Data Index: 1015068 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1231. Min Act: -0.0001

Data Index: 98201 (C4 (Web Text))

Max Activating Token Index: 407