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

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

Neuron 4470 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.3064. Min Act: -0.0002

Data Index: 979838 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2989. Min Act: -0.0002

Data Index: 1214254 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2709. Min Act: -0.0002

Data Index: 71174 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.3007. Min Act: -0.0002

Data Index: 978762 (C4 (Web Text))

Max Activating Token Index: 324

Text #4

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2813. Min Act: -0.0002

Data Index: 1157503 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2935. Min Act: -0.0002

Data Index: 297091 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2770. Min Act: -0.0002

Data Index: 598413 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2562. Min Act: -0.0002

Data Index: 36846 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2707. Min Act: -0.0002

Data Index: 583836 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2722. Min Act: -0.0002

Data Index: 688928 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2622. Min Act: -0.0002

Data Index: 353217 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2528. Min Act: -0.0002

Data Index: 1153660 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2399. Min Act: -0.0002

Data Index: 199457 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2610. Min Act: -0.0002

Data Index: 499033 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2604. Min Act: -0.0002

Data Index: 1189065 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2528. Min Act: -0.0002

Data Index: 748056 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2402. Min Act: -0.0002

Data Index: 1251278 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2330. Min Act: -0.0002

Data Index: 319495 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2239. Min Act: -0.0002

Data Index: 702105 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2453. Min Act: -0.0002

Data Index: 902730 (C4 (Web Text))

Max Activating Token Index: 348