Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 406 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.7548. Min Range: -3.7548

Max Act: 3.7235. Min Act: -0.1700

Data Index: 321493 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 3.7548. Min Range: -3.7548

Max Act: 3.7548. Min Act: -0.1700

Data Index: 429513 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 3.7548. Min Range: -3.7548

Max Act: 3.6609. Min Act: -0.1700

Data Index: 1079242 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 3.7548. Min Range: -3.7548

Max Act: 3.5983. Min Act: -0.1700

Data Index: 1199587 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 3.7548. Min Range: -3.7548

Max Act: 3.6296. Min Act: -0.1700

Data Index: 367437 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 3.7548. Min Range: -3.7548

Max Act: 3.5670. Min Act: -0.1700

Data Index: 1212689 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 3.7548. Min Range: -3.7548

Max Act: 3.5983. Min Act: -0.1700

Data Index: 546644 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 3.7548. Min Range: -3.7548

Max Act: 3.6296. Min Act: -0.1700

Data Index: 112770 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 3.7548. Min Range: -3.7548

Max Act: 3.6296. Min Act: -0.1700

Data Index: 584306 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 3.7548. Min Range: -3.7548

Max Act: 3.5983. Min Act: -0.1700

Data Index: 377346 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 3.7548. Min Range: -3.7548

Max Act: 3.5983. Min Act: -0.1700

Data Index: 452471 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 3.7548. Min Range: -3.7548

Max Act: 3.5670. Min Act: -0.1700

Data Index: 1357725 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 3.7548. Min Range: -3.7548

Max Act: 3.5983. Min Act: -0.1700

Data Index: 764779 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 3.7548. Min Range: -3.7548

Max Act: 3.5983. Min Act: -0.1700

Data Index: 183833 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 3.7548. Min Range: -3.7548

Max Act: 3.5356. Min Act: -0.1700

Data Index: 1316963 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 3.7548. Min Range: -3.7548

Max Act: 3.5356. Min Act: -0.1700

Data Index: 865477 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 3.7548. Min Range: -3.7548

Max Act: 3.5043. Min Act: -0.1700

Data Index: 721060 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 3.7548. Min Range: -3.7548

Max Act: 3.5670. Min Act: -0.1700

Data Index: 1318102 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 3.7548. Min Range: -3.7548

Max Act: 3.5983. Min Act: -0.1700

Data Index: 809365 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 3.7548. Min Range: -3.7548

Max Act: 3.5356. Min Act: -0.1700

Data Index: 363228 (C4 (Web Text))

Max Activating Token Index: 997