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

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

Neuron 2323 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: 0.1918. Min Range: -0.1918

Max Act: 0.1918. Min Act: -0.0001

Data Index: 22469 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1700. Min Act: -0.0001

Data Index: 41354 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1500. Min Act: -0.0001

Data Index: 915267 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1576. Min Act: -0.0001

Data Index: 222353 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1533. Min Act: -0.0001

Data Index: 1302694 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1518. Min Act: -0.0001

Data Index: 822048 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1490. Min Act: -0.0001

Data Index: 12325 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1480. Min Act: -0.0001

Data Index: 1235945 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1369. Min Act: -0.0001

Data Index: 263947 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1402. Min Act: -0.0001

Data Index: 93966 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1366. Min Act: -0.0001

Data Index: 1284165 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1410. Min Act: -0.0001

Data Index: 109093 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1422. Min Act: -0.0001

Data Index: 1121494 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1371. Min Act: -0.0001

Data Index: 1087217 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1351. Min Act: -0.0001

Data Index: 747484 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1337. Min Act: -0.0001

Data Index: 179452 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1371. Min Act: -0.0001

Data Index: 580232 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1334. Min Act: -0.0001

Data Index: 736107 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1377. Min Act: -0.0001

Data Index: 1351048 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1474. Min Act: -0.0001

Data Index: 40791 (C4 (Web Text))

Max Activating Token Index: 873