Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2762 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1592. Min Act: -0.0001

Data Index: 428338 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1576. Min Act: -0.0000

Data Index: 751409 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1532. Min Act: 0.0000

Data Index: 1072822 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1537. Min Act: -0.0000

Data Index: 323288 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1470. Min Act: -0.0000

Data Index: 710560 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1422. Min Act: -0.0000

Data Index: 983988 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1521. Min Act: 0.0001

Data Index: 1185088 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1407. Min Act: -0.0000

Data Index: 296315 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1359. Min Act: -0.0000

Data Index: 1276451 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1383. Min Act: -0.0000

Data Index: 1259924 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1420. Min Act: -0.0001

Data Index: 1149132 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1410. Min Act: -0.0000

Data Index: 350205 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1392. Min Act: -0.0000

Data Index: 103989 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1345. Min Act: -0.0000

Data Index: 849064 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1334. Min Act: 0.0000

Data Index: 786314 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1323. Min Act: -0.0000

Data Index: 1043461 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1328. Min Act: -0.0000

Data Index: 535084 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1324. Min Act: -0.0000

Data Index: 775707 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1269. Min Act: -0.0000

Data Index: 303605 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1220. Min Act: -0.0000

Data Index: 265819 (C4 (Web Text))

Max Activating Token Index: 630