Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1929 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.4403. Min Act: -0.0000

Data Index: 467294 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.4372. Min Act: -0.0000

Data Index: 638103 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.4117. Min Act: -0.0000

Data Index: 755413 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.4348. Min Act: -0.0000

Data Index: 794595 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.4164. Min Act: -0.0000

Data Index: 862710 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.3736. Min Act: -0.0000

Data Index: 1326834 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.3872. Min Act: -0.0000

Data Index: 1346327 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.4123. Min Act: -0.0000

Data Index: 1262079 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.3890. Min Act: -0.0000

Data Index: 733932 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.4005. Min Act: -0.0000

Data Index: 598696 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.3912. Min Act: -0.0000

Data Index: 271091 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.3735. Min Act: -0.0000

Data Index: 294287 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.3730. Min Act: -0.0000

Data Index: 255221 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.3918. Min Act: -0.0000

Data Index: 111644 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.3954. Min Act: -0.0000

Data Index: 1239102 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.3706. Min Act: -0.0000

Data Index: 114534 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.3932. Min Act: -0.0000

Data Index: 800691 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.3769. Min Act: -0.0001

Data Index: 511346 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.4069. Min Act: -0.0000

Data Index: 375050 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.3770. Min Act: -0.0000

Data Index: 705118 (C4 (Web Text))

Max Activating Token Index: 920