Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2643 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.2131. Min Act: -0.0000

Data Index: 1039167 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.2090. Min Act: -0.0000

Data Index: 767091 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.1518. Min Act: -0.0000

Data Index: 926626 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.0602. Min Act: -0.0000

Data Index: 31025 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.1140. Min Act: -0.0000

Data Index: 1178694 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9888. Min Act: -0.0000

Data Index: 1114211 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.0054. Min Act: -0.0000

Data Index: 762042 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9758. Min Act: -0.0000

Data Index: 1116765 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9002. Min Act: -0.0000

Data Index: 474469 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.0058. Min Act: -0.0000

Data Index: 416513 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9514. Min Act: -0.0000

Data Index: 369502 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9478. Min Act: -0.0000

Data Index: 1058566 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9521. Min Act: -0.0000

Data Index: 478467 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9334. Min Act: -0.0000

Data Index: 178694 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9559. Min Act: -0.0000

Data Index: 449429 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9266. Min Act: -0.0000

Data Index: 403183 (C4 (Web Text))

Max Activating Token Index: 1021

Text #16

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.8838. Min Act: -0.0001

Data Index: 905866 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9560. Min Act: -0.0000

Data Index: 868108 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.8858. Min Act: -0.0001

Data Index: 323010 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.8797. Min Act: -0.0000

Data Index: 970452 (C4 (Web Text))

Max Activating Token Index: 125