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

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

Neuron 4193 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.8367. Min Act: -0.0000

Data Index: 249633 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.7382. Min Act: -0.0000

Data Index: 1042471 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.6453. Min Act: -0.0000

Data Index: 1193574 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.5935. Min Act: -0.0000

Data Index: 629026 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.6035. Min Act: -0.0000

Data Index: 213400 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.5382. Min Act: -0.0000

Data Index: 789385 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.5370. Min Act: -0.0000

Data Index: 1092321 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.4696. Min Act: -0.0000

Data Index: 1118862 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.5468. Min Act: -0.0000

Data Index: 912934 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.3794. Min Act: -0.0000

Data Index: 918890 (C4 (Web Text))

Max Activating Token Index: 1015

Text #10

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.3000. Min Act: -0.0001

Data Index: 924091 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.3991. Min Act: -0.0000

Data Index: 617168 (C4 (Web Text))

Max Activating Token Index: 403

Text #12

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.3912. Min Act: -0.0001

Data Index: 147375 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.3222. Min Act: -0.0000

Data Index: 984743 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.3888. Min Act: -0.0000

Data Index: 1222751 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.3380. Min Act: -0.0000

Data Index: 202926 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.3386. Min Act: -0.0000

Data Index: 862086 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.3735. Min Act: -0.0000

Data Index: 1345852 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.2849. Min Act: -0.0000

Data Index: 803596 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.4384. Min Act: -0.0000

Data Index: 981900 (C4 (Web Text))

Max Activating Token Index: 503