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

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

Neuron 3967 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: 5.2365. Min Range: -5.2365

Max Act: 5.2347. Min Act: -0.0000

Data Index: 988730 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 5.2365. Min Range: -5.2365

Max Act: 5.2365. Min Act: -0.0000

Data Index: 1121840 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 5.2365. Min Range: -5.2365

Max Act: 5.1509. Min Act: -0.0000

Data Index: 394671 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 5.2365. Min Range: -5.2365

Max Act: 5.2309. Min Act: -0.0000

Data Index: 348557 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 5.2365. Min Range: -5.2365

Max Act: 4.9956. Min Act: -0.0000

Data Index: 313541 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 5.2365. Min Range: -5.2365

Max Act: 4.9136. Min Act: -0.0000

Data Index: 1346987 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 5.2365. Min Range: -5.2365

Max Act: 4.7411. Min Act: -0.0000

Data Index: 998532 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 5.2365. Min Range: -5.2365

Max Act: 4.7415. Min Act: -0.0000

Data Index: 908741 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 5.2365. Min Range: -5.2365

Max Act: 4.7284. Min Act: -0.0000

Data Index: 1240 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 5.2365. Min Range: -5.2365

Max Act: 4.2399. Min Act: -0.0000

Data Index: 778980 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 5.2365. Min Range: -5.2365

Max Act: 4.5491. Min Act: -0.0000

Data Index: 842625 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 5.2365. Min Range: -5.2365

Max Act: 4.3630. Min Act: -0.0000

Data Index: 1330783 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 5.2365. Min Range: -5.2365

Max Act: 4.2699. Min Act: -0.0000

Data Index: 846489 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 5.2365. Min Range: -5.2365

Max Act: 3.9386. Min Act: -0.0000

Data Index: 921193 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 5.2365. Min Range: -5.2365

Max Act: 4.0789. Min Act: -0.0000

Data Index: 1043574 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 5.2365. Min Range: -5.2365

Max Act: 4.0324. Min Act: -0.0000

Data Index: 487082 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 5.2365. Min Range: -5.2365

Max Act: 4.1966. Min Act: -0.0000

Data Index: 268708 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 5.2365. Min Range: -5.2365

Max Act: 4.1615. Min Act: -0.0000

Data Index: 1246450 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 5.2365. Min Range: -5.2365

Max Act: 4.2057. Min Act: -0.0000

Data Index: 550222 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 5.2365. Min Range: -5.2365

Max Act: 4.1809. Min Act: -0.0000

Data Index: 1257570 (C4 (Web Text))

Max Activating Token Index: 523