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

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

Neuron 5803 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: 4.5925. Min Range: -4.5925

Max Act: 4.5925. Min Act: -0.0000

Data Index: 69792 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 4.5925. Min Range: -4.5925

Max Act: 3.4906. Min Act: -0.0000

Data Index: 1352389 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 4.5925. Min Range: -4.5925

Max Act: 3.4671. Min Act: -0.0000

Data Index: 38738 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 4.5925. Min Range: -4.5925

Max Act: 2.8502. Min Act: -0.0000

Data Index: 237644 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 4.5925. Min Range: -4.5925

Max Act: 3.1128. Min Act: -0.0000

Data Index: 642231 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 4.5925. Min Range: -4.5925

Max Act: 2.7142. Min Act: -0.0000

Data Index: 284464 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 4.5925. Min Range: -4.5925

Max Act: 2.6459. Min Act: -0.0000

Data Index: 235356 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 4.5925. Min Range: -4.5925

Max Act: 2.7450. Min Act: -0.0000

Data Index: 1336109 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 4.5925. Min Range: -4.5925

Max Act: 2.5426. Min Act: -0.0000

Data Index: 945415 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 4.5925. Min Range: -4.5925

Max Act: 2.6428. Min Act: -0.0000

Data Index: 953898 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 4.5925. Min Range: -4.5925

Max Act: 2.5212. Min Act: -0.0000

Data Index: 65488 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 4.5925. Min Range: -4.5925

Max Act: 2.2943. Min Act: -0.0000

Data Index: 946337 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 4.5925. Min Range: -4.5925

Max Act: 2.3941. Min Act: -0.0000

Data Index: 820371 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 4.5925. Min Range: -4.5925

Max Act: 2.2419. Min Act: -0.0000

Data Index: 270666 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 4.5925. Min Range: -4.5925

Max Act: 2.2583. Min Act: -0.0000

Data Index: 355479 (C4 (Web Text))

Max Activating Token Index: 310

Text #15

Max Range: 4.5925. Min Range: -4.5925

Max Act: 2.3640. Min Act: -0.0000

Data Index: 758166 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 4.5925. Min Range: -4.5925

Max Act: 2.0782. Min Act: -0.0000

Data Index: 1222847 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 4.5925. Min Range: -4.5925

Max Act: 2.4319. Min Act: -0.0000

Data Index: 202188 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 4.5925. Min Range: -4.5925

Max Act: 2.2054. Min Act: -0.0000

Data Index: 650604 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 4.5925. Min Range: -4.5925

Max Act: 2.2013. Min Act: -0.0000

Data Index: 302642 (C4 (Web Text))

Max Activating Token Index: 800