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

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

Neuron 785 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4233. Min Range: -2.4233

Max Act: 2.4233. Min Act: -0.0000

Data Index: 514284 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 2.4233. Min Range: -2.4233

Max Act: 1.9650. Min Act: -0.0000

Data Index: 252130 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 2.4233. Min Range: -2.4233

Max Act: 1.9005. Min Act: -0.0000

Data Index: 768427 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 2.4233. Min Range: -2.4233

Max Act: 1.8507. Min Act: -0.0000

Data Index: 161460 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 2.4233. Min Range: -2.4233

Max Act: 1.8136. Min Act: -0.0000

Data Index: 924577 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 2.4233. Min Range: -2.4233

Max Act: 1.7573. Min Act: -0.0000

Data Index: 444471 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 2.4233. Min Range: -2.4233

Max Act: 1.6444. Min Act: -0.0000

Data Index: 288852 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 2.4233. Min Range: -2.4233

Max Act: 1.7317. Min Act: -0.0000

Data Index: 1346780 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 2.4233. Min Range: -2.4233

Max Act: 1.7649. Min Act: -0.0000

Data Index: 915154 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 2.4233. Min Range: -2.4233

Max Act: 1.5271. Min Act: -0.0000

Data Index: 729301 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 2.4233. Min Range: -2.4233

Max Act: 1.5399. Min Act: -0.0000

Data Index: 678724 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 2.4233. Min Range: -2.4233

Max Act: 1.4331. Min Act: -0.0000

Data Index: 843001 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 2.4233. Min Range: -2.4233

Max Act: 1.5942. Min Act: -0.0000

Data Index: 135964 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 2.4233. Min Range: -2.4233

Max Act: 1.4815. Min Act: -0.0000

Data Index: 194622 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 2.4233. Min Range: -2.4233

Max Act: 1.4149. Min Act: -0.0000

Data Index: 439835 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 2.4233. Min Range: -2.4233

Max Act: 1.3325. Min Act: -0.0000

Data Index: 461985 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 2.4233. Min Range: -2.4233

Max Act: 1.3232. Min Act: -0.0000

Data Index: 185902 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 2.4233. Min Range: -2.4233

Max Act: 1.2876. Min Act: -0.0000

Data Index: 504074 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 2.4233. Min Range: -2.4233

Max Act: 1.3274. Min Act: -0.0000

Data Index: 794924 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 2.4233. Min Range: -2.4233

Max Act: 1.3439. Min Act: -0.0000

Data Index: 106313 (C4 (Web Text))

Max Activating Token Index: 329