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

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

Neuron 2643 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: 5.0849. Min Range: -5.0849

Max Act: 5.0849. Min Act: -0.0000

Data Index: 1108042 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 5.0849. Min Range: -5.0849

Max Act: 4.6447. Min Act: -0.0000

Data Index: 1219877 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 5.0849. Min Range: -5.0849

Max Act: 3.4716. Min Act: -0.0000

Data Index: 500720 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 5.0849. Min Range: -5.0849

Max Act: 3.7825. Min Act: -0.0000

Data Index: 121833 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 5.0849. Min Range: -5.0849

Max Act: 3.3956. Min Act: -0.0000

Data Index: 361144 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 5.0849. Min Range: -5.0849

Max Act: 3.6851. Min Act: -0.0000

Data Index: 1109078 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 5.0849. Min Range: -5.0849

Max Act: 3.4335. Min Act: -0.0000

Data Index: 677972 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 5.0849. Min Range: -5.0849

Max Act: 3.1926. Min Act: -0.0000

Data Index: 559114 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 5.0849. Min Range: -5.0849

Max Act: 3.2943. Min Act: -0.0000

Data Index: 409782 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 5.0849. Min Range: -5.0849

Max Act: 3.3909. Min Act: -0.0000

Data Index: 1100373 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 5.0849. Min Range: -5.0849

Max Act: 3.0817. Min Act: -0.0000

Data Index: 304992 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 5.0849. Min Range: -5.0849

Max Act: 3.2288. Min Act: -0.0000

Data Index: 375290 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 5.0849. Min Range: -5.0849

Max Act: 3.2156. Min Act: -0.0000

Data Index: 705730 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 5.0849. Min Range: -5.0849

Max Act: 3.1831. Min Act: -0.0000

Data Index: 116702 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 5.0849. Min Range: -5.0849

Max Act: 3.1946. Min Act: -0.0000

Data Index: 681081 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 5.0849. Min Range: -5.0849

Max Act: 3.1574. Min Act: -0.0000

Data Index: 566985 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 5.0849. Min Range: -5.0849

Max Act: 2.9074. Min Act: -0.0000

Data Index: 138120 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 5.0849. Min Range: -5.0849

Max Act: 3.3367. Min Act: -0.0000

Data Index: 1059497 (C4 (Web Text))

Max Activating Token Index: 422

Text #18

Max Range: 5.0849. Min Range: -5.0849

Max Act: 2.9916. Min Act: -0.0000

Data Index: 856484 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 5.0849. Min Range: -5.0849

Max Act: 3.1204. Min Act: -0.0000

Data Index: 836559 (C4 (Web Text))

Max Activating Token Index: 459