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

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

Neuron 3560 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8449. Min Range: -2.8449

Max Act: 2.8449. Min Act: -0.0000

Data Index: 1286318 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 2.8449. Min Range: -2.8449

Max Act: 2.4625. Min Act: -0.0000

Data Index: 875160 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 2.8449. Min Range: -2.8449

Max Act: 2.3601. Min Act: -0.0000

Data Index: 790332 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 2.8449. Min Range: -2.8449

Max Act: 2.2507. Min Act: -0.0000

Data Index: 1130383 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 2.8449. Min Range: -2.8449

Max Act: 2.3479. Min Act: -0.0000

Data Index: 1094620 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 2.8449. Min Range: -2.8449

Max Act: 2.1993. Min Act: -0.0000

Data Index: 190606 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 2.8449. Min Range: -2.8449

Max Act: 2.1871. Min Act: -0.0000

Data Index: 156182 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 2.8449. Min Range: -2.8449

Max Act: 2.3065. Min Act: -0.0000

Data Index: 399962 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 2.8449. Min Range: -2.8449

Max Act: 2.1351. Min Act: -0.0000

Data Index: 1328298 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 2.8449. Min Range: -2.8449

Max Act: 2.0612. Min Act: -0.0000

Data Index: 1308800 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 2.8449. Min Range: -2.8449

Max Act: 2.1117. Min Act: -0.0000

Data Index: 18739 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 2.8449. Min Range: -2.8449

Max Act: 2.0330. Min Act: -0.0000

Data Index: 1090561 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 2.8449. Min Range: -2.8449

Max Act: 2.1071. Min Act: -0.0000

Data Index: 1329481 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 2.8449. Min Range: -2.8449

Max Act: 2.1897. Min Act: -0.0000

Data Index: 872859 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 2.8449. Min Range: -2.8449

Max Act: 2.0739. Min Act: -0.0000

Data Index: 467584 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 2.8449. Min Range: -2.8449

Max Act: 2.1326. Min Act: -0.0000

Data Index: 861190 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 2.8449. Min Range: -2.8449

Max Act: 2.0958. Min Act: 0.0000

Data Index: 927709 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 2.8449. Min Range: -2.8449

Max Act: 2.1193. Min Act: -0.0000

Data Index: 1291778 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 2.8449. Min Range: -2.8449

Max Act: 2.0399. Min Act: 0.0000

Data Index: 1055482 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 2.8449. Min Range: -2.8449

Max Act: 2.0332. Min Act: -0.0000

Data Index: 926873 (C4 (Web Text))

Max Activating Token Index: 333