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

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

Neuron 1827 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: 0.1493. Min Range: -0.1493

Max Act: 0.1461. Min Act: -0.0001

Data Index: 1345661 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1493. Min Act: -0.0001

Data Index: 1137713 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1411. Min Act: -0.0001

Data Index: 811139 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1345. Min Act: -0.0001

Data Index: 431333 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1287. Min Act: -0.0001

Data Index: 597569 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1315. Min Act: -0.0001

Data Index: 1273877 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1274. Min Act: -0.0001

Data Index: 577086 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1248. Min Act: -0.0001

Data Index: 1185597 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1321. Min Act: -0.0001

Data Index: 819920 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1258. Min Act: -0.0001

Data Index: 82063 (C4 (Web Text))

Max Activating Token Index: 391

Text #10

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1308. Min Act: -0.0001

Data Index: 548154 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1239. Min Act: -0.0001

Data Index: 198992 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1244. Min Act: -0.0001

Data Index: 952441 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1280. Min Act: -0.0001

Data Index: 51860 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1275. Min Act: -0.0001

Data Index: 67088 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1237. Min Act: -0.0001

Data Index: 117031 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1208. Min Act: -0.0001

Data Index: 888182 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1248. Min Act: -0.0001

Data Index: 521721 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1265. Min Act: -0.0001

Data Index: 1178792 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1233. Min Act: -0.0001

Data Index: 1137666 (C4 (Web Text))

Max Activating Token Index: 95