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

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

Neuron 2352 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: 2.4325. Min Range: -2.4325

Max Act: 2.4325. Min Act: -0.0000

Data Index: 1013712 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 2.4325. Min Range: -2.4325

Max Act: 2.1887. Min Act: -0.0000

Data Index: 859429 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 2.4325. Min Range: -2.4325

Max Act: 2.1573. Min Act: -0.0000

Data Index: 348528 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 2.4325. Min Range: -2.4325

Max Act: 1.9584. Min Act: -0.0000

Data Index: 578655 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 2.4325. Min Range: -2.4325

Max Act: 1.8404. Min Act: -0.0000

Data Index: 1163081 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 2.4325. Min Range: -2.4325

Max Act: 2.0208. Min Act: -0.0000

Data Index: 1334799 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 2.4325. Min Range: -2.4325

Max Act: 1.9860. Min Act: -0.0000

Data Index: 101302 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 2.4325. Min Range: -2.4325

Max Act: 1.9287. Min Act: -0.0000

Data Index: 155609 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 2.4325. Min Range: -2.4325

Max Act: 1.8833. Min Act: -0.0000

Data Index: 433672 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 2.4325. Min Range: -2.4325

Max Act: 1.8520. Min Act: -0.0000

Data Index: 142668 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 2.4325. Min Range: -2.4325

Max Act: 1.8120. Min Act: -0.0000

Data Index: 959275 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 2.4325. Min Range: -2.4325

Max Act: 1.9093. Min Act: -0.0000

Data Index: 742707 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 2.4325. Min Range: -2.4325

Max Act: 1.6390. Min Act: -0.0000

Data Index: 224068 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 2.4325. Min Range: -2.4325

Max Act: 1.6291. Min Act: -0.0000

Data Index: 758977 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 2.4325. Min Range: -2.4325

Max Act: 1.6967. Min Act: -0.0000

Data Index: 378533 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 2.4325. Min Range: -2.4325

Max Act: 1.6700. Min Act: -0.0000

Data Index: 352010 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 2.4325. Min Range: -2.4325

Max Act: 1.6409. Min Act: -0.0000

Data Index: 1246896 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 2.4325. Min Range: -2.4325

Max Act: 1.6427. Min Act: -0.0000

Data Index: 519124 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 2.4325. Min Range: -2.4325

Max Act: 1.5927. Min Act: -0.0000

Data Index: 128882 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 2.4325. Min Range: -2.4325

Max Act: 1.5644. Min Act: -0.0000

Data Index: 482169 (C4 (Web Text))

Max Activating Token Index: 889