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

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

Neuron 2804 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: 0.3280. Min Range: -0.3280

Max Act: 0.3280. Min Act: -0.0000

Data Index: 286747 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2882. Min Act: -0.0000

Data Index: 1333840 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.3244. Min Act: -0.0000

Data Index: 231825 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2929. Min Act: -0.0000

Data Index: 1457281 (Python Code)

Max Activating Token Index: 558

Text #4

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2893. Min Act: -0.0000

Data Index: 188622 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1183899 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2858. Min Act: -0.0000

Data Index: 647560 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2645. Min Act: 0.0000

Data Index: 889544 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2876. Min Act: -0.0000

Data Index: 1249693 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2791. Min Act: -0.0000

Data Index: 827908 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2690. Min Act: -0.0000

Data Index: 925907 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.3036. Min Act: -0.0000

Data Index: 765126 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2879. Min Act: -0.0000

Data Index: 173193 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2660. Min Act: -0.0000

Data Index: 1098297 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2685. Min Act: -0.0000

Data Index: 1135065 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2574. Min Act: -0.0000

Data Index: 366336 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2528. Min Act: -0.0000

Data Index: 651226 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2864. Min Act: -0.0000

Data Index: 840310 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2543. Min Act: -0.0000

Data Index: 1615558 (Python Code)

Max Activating Token Index: 390

Text #19

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2564. Min Act: -0.0000

Data Index: 493925 (C4 (Web Text))

Max Activating Token Index: 441