Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2456 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.5397. Min Act: -0.0001

Data Index: 632597 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.5035. Min Act: -0.0001

Data Index: 537285 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4708. Min Act: -0.0001

Data Index: 1157659 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4956. Min Act: -0.0001

Data Index: 296240 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4509. Min Act: -0.0001

Data Index: 1304676 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4566. Min Act: -0.0001

Data Index: 1323634 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4469. Min Act: -0.0001

Data Index: 29146 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4376. Min Act: -0.0001

Data Index: 279273 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4463. Min Act: -0.0001

Data Index: 884218 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4447. Min Act: -0.0001

Data Index: 676870 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4233. Min Act: -0.0001

Data Index: 1104493 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4138. Min Act: -0.0001

Data Index: 304864 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4316. Min Act: -0.0001

Data Index: 208780 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.3928. Min Act: -0.0001

Data Index: 1205315 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4103. Min Act: -0.0001

Data Index: 1115428 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4055. Min Act: -0.0001

Data Index: 439070 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4062. Min Act: -0.0001

Data Index: 419173 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4098. Min Act: -0.0001

Data Index: 657578 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4248. Min Act: -0.0001

Data Index: 493478 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4395. Min Act: -0.0001

Data Index: 162580 (C4 (Web Text))

Max Activating Token Index: 247