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

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

Neuron 2140 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7244. Min Range: -5.7244

Max Act: 5.7244. Min Act: -0.0000

Data Index: 635187 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 5.7244. Min Range: -5.7244

Max Act: 5.2621. Min Act: -0.0000

Data Index: 75082 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 5.7244. Min Range: -5.7244

Max Act: 4.9868. Min Act: -0.0000

Data Index: 1181422 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 5.7244. Min Range: -5.7244

Max Act: 5.5494. Min Act: -0.0000

Data Index: 933091 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 5.7244. Min Range: -5.7244

Max Act: 5.3189. Min Act: -0.0000

Data Index: 472285 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 5.7244. Min Range: -5.7244

Max Act: 4.9895. Min Act: -0.0000

Data Index: 98591 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 5.7244. Min Range: -5.7244

Max Act: 5.0921. Min Act: -0.0000

Data Index: 373309 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 5.7244. Min Range: -5.7244

Max Act: 5.1670. Min Act: -0.0000

Data Index: 994384 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 5.7244. Min Range: -5.7244

Max Act: 4.7197. Min Act: -0.0000

Data Index: 91527 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 5.7244. Min Range: -5.7244

Max Act: 4.8320. Min Act: -0.0000

Data Index: 109662 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 5.7244. Min Range: -5.7244

Max Act: 4.8604. Min Act: -0.0000

Data Index: 1305952 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 5.7244. Min Range: -5.7244

Max Act: 4.7663. Min Act: -0.0000

Data Index: 549304 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 5.7244. Min Range: -5.7244

Max Act: 4.9926. Min Act: -0.0000

Data Index: 985188 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 5.7244. Min Range: -5.7244

Max Act: 4.7214. Min Act: -0.0000

Data Index: 397873 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 5.7244. Min Range: -5.7244

Max Act: 4.2714. Min Act: -0.0000

Data Index: 730339 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 5.7244. Min Range: -5.7244

Max Act: 4.4425. Min Act: -0.0000

Data Index: 807238 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 5.7244. Min Range: -5.7244

Max Act: 4.6092. Min Act: -0.0000

Data Index: 235354 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 5.7244. Min Range: -5.7244

Max Act: 4.5654. Min Act: -0.0000

Data Index: 60171 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 5.7244. Min Range: -5.7244

Max Act: 4.3361. Min Act: -0.0000

Data Index: 267323 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 5.7244. Min Range: -5.7244

Max Act: 4.5380. Min Act: -0.0000

Data Index: 241981 (C4 (Web Text))

Max Activating Token Index: 980