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

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

Neuron 5287 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: 0.3713. Min Range: -0.3713

Max Act: 0.3713. Min Act: -0.0000

Data Index: 334251 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.3612. Min Act: -0.0000

Data Index: 88051 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.3256. Min Act: -0.0000

Data Index: 1563867 (Python Code)

Max Activating Token Index: 996

Text #3

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2933. Min Act: -0.0000

Data Index: 271162 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2696. Min Act: -0.0000

Data Index: 641422 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2758. Min Act: -0.0000

Data Index: 956213 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2674. Min Act: -0.0000

Data Index: 955953 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2732. Min Act: -0.0000

Data Index: 454915 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2464. Min Act: -0.0000

Data Index: 390479 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2469. Min Act: -0.0000

Data Index: 234277 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2282. Min Act: -0.0000

Data Index: 102221 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2103. Min Act: -0.0000

Data Index: 1560266 (Python Code)

Max Activating Token Index: 576

Text #12

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2296. Min Act: -0.0000

Data Index: 378399 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2226. Min Act: -0.0000

Data Index: 446114 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2211. Min Act: -0.0000

Data Index: 1078466 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2270. Min Act: -0.0000

Data Index: 128931 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2339. Min Act: -0.0000

Data Index: 945258 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2197. Min Act: -0.0000

Data Index: 1401029 (Python Code)

Max Activating Token Index: 117

Text #18

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.1984. Min Act: -0.0000

Data Index: 723725 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2108. Min Act: -0.0000

Data Index: 354746 (C4 (Web Text))

Max Activating Token Index: 513