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

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

Neuron 5990 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.5437. Min Act: -0.0000

Data Index: 538695 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4512. Min Act: -0.0000

Data Index: 597833 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4617. Min Act: -0.0000

Data Index: 711566 (C4 (Web Text))

Max Activating Token Index: 516

Text #3

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4164. Min Act: -0.0000

Data Index: 4491 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4261. Min Act: -0.0000

Data Index: 274227 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3825. Min Act: -0.0000

Data Index: 892400 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4017. Min Act: -0.0000

Data Index: 123432 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4128. Min Act: -0.0000

Data Index: 426930 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3910. Min Act: -0.0000

Data Index: 1145248 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3821. Min Act: -0.0000

Data Index: 81320 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3751. Min Act: -0.0000

Data Index: 989386 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3759. Min Act: -0.0000

Data Index: 1281780 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3750. Min Act: -0.0000

Data Index: 71224 (C4 (Web Text))

Max Activating Token Index: 407

Text #13

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3742. Min Act: -0.0000

Data Index: 692405 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3722. Min Act: -0.0000

Data Index: 654597 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3747. Min Act: -0.0000

Data Index: 530441 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3582. Min Act: -0.0000

Data Index: 228189 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3565. Min Act: -0.0000

Data Index: 180860 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3474. Min Act: -0.0000

Data Index: 1183658 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3804. Min Act: -0.0000

Data Index: 489112 (C4 (Web Text))

Max Activating Token Index: 548