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

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

Neuron 1432 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1317. Min Act: -0.0001

Data Index: 66452 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1313. Min Act: -0.0001

Data Index: 1121548 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1318. Min Act: -0.0001

Data Index: 532040 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1296. Min Act: -0.0001

Data Index: 576742 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1243. Min Act: -0.0001

Data Index: 453775 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1287. Min Act: -0.0001

Data Index: 709985 (C4 (Web Text))

Max Activating Token Index: 1001

Text #6

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1371. Min Act: -0.0001

Data Index: 368034 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1229. Min Act: -0.0001

Data Index: 1356085 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1205. Min Act: -0.0001

Data Index: 634203 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1260. Min Act: -0.0001

Data Index: 600657 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1216. Min Act: -0.0001

Data Index: 453863 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1330. Min Act: -0.0001

Data Index: 1181266 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1216. Min Act: -0.0001

Data Index: 862584 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1272. Min Act: -0.0001

Data Index: 230583 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1236. Min Act: -0.0001

Data Index: 122638 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1273. Min Act: -0.0001

Data Index: 236958 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1292. Min Act: -0.0001

Data Index: 1286932 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1234. Min Act: -0.0001

Data Index: 1318877 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1206. Min Act: -0.0001

Data Index: 1184358 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1245. Min Act: -0.0001

Data Index: 675447 (C4 (Web Text))

Max Activating Token Index: 451