Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1145 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.9452. Min Act: -0.0000

Data Index: 52692 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.8148. Min Act: -0.0000

Data Index: 1176225 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.8085. Min Act: -0.0000

Data Index: 302110 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.7240. Min Act: -0.0000

Data Index: 1284634 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.7220. Min Act: -0.0000

Data Index: 1242014 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.7239. Min Act: -0.0000

Data Index: 171778 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6772. Min Act: -0.0000

Data Index: 1301570 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6791. Min Act: -0.0000

Data Index: 1330739 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6502. Min Act: -0.0000

Data Index: 926927 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6812. Min Act: -0.0000

Data Index: 254023 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6383. Min Act: -0.0000

Data Index: 62650 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6304. Min Act: -0.0000

Data Index: 894810 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6439. Min Act: -0.0000

Data Index: 1270770 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6395. Min Act: -0.0000

Data Index: 1157941 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6227. Min Act: -0.0000

Data Index: 374324 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6113. Min Act: -0.0000

Data Index: 161287 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.5900. Min Act: -0.0000

Data Index: 401579 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6342. Min Act: -0.0000

Data Index: 602891 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.5045. Min Act: -0.0000

Data Index: 784768 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6164. Min Act: -0.0000

Data Index: 848260 (C4 (Web Text))

Max Activating Token Index: 725