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

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

Neuron 2379 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.2551. Min Range: -6.2551

Max Act: 6.2551. Min Act: -0.0000

Data Index: 1257607 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 6.2551. Min Range: -6.2551

Max Act: 4.8577. Min Act: -0.0000

Data Index: 688104 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 6.2551. Min Range: -6.2551

Max Act: 4.1385. Min Act: -0.0000

Data Index: 105176 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 6.2551. Min Range: -6.2551

Max Act: 3.4538. Min Act: -0.0000

Data Index: 1090986 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 6.2551. Min Range: -6.2551

Max Act: 3.2786. Min Act: -0.0000

Data Index: 1078554 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 6.2551. Min Range: -6.2551

Max Act: 3.4277. Min Act: -0.0000

Data Index: 945319 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 6.2551. Min Range: -6.2551

Max Act: 3.4194. Min Act: -0.0000

Data Index: 81080 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 6.2551. Min Range: -6.2551

Max Act: 3.2149. Min Act: -0.0000

Data Index: 957951 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 6.2551. Min Range: -6.2551

Max Act: 3.5009. Min Act: -0.0000

Data Index: 807866 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 6.2551. Min Range: -6.2551

Max Act: 3.3197. Min Act: -0.0000

Data Index: 883819 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 6.2551. Min Range: -6.2551

Max Act: 3.2925. Min Act: -0.0000

Data Index: 231768 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 6.2551. Min Range: -6.2551

Max Act: 3.2613. Min Act: -0.0000

Data Index: 452451 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 6.2551. Min Range: -6.2551

Max Act: 3.2200. Min Act: -0.0000

Data Index: 311062 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 6.2551. Min Range: -6.2551

Max Act: 3.1953. Min Act: -0.0000

Data Index: 829430 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 6.2551. Min Range: -6.2551

Max Act: 3.2053. Min Act: -0.0000

Data Index: 1096204 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 6.2551. Min Range: -6.2551

Max Act: 3.1097. Min Act: -0.0000

Data Index: 168921 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 6.2551. Min Range: -6.2551

Max Act: 3.0042. Min Act: -0.0000

Data Index: 393690 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 6.2551. Min Range: -6.2551

Max Act: 2.8304. Min Act: -0.0000

Data Index: 1151572 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 6.2551. Min Range: -6.2551

Max Act: 2.9899. Min Act: -0.0000

Data Index: 808079 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 6.2551. Min Range: -6.2551

Max Act: 2.9602. Min Act: -0.0000

Data Index: 741097 (C4 (Web Text))

Max Activating Token Index: 886