Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1220 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 4.4397. Min Range: -4.4397

Max Act: 4.4397. Min Act: -0.1700

Data Index: 1183715 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 4.4397. Min Range: -4.4397

Max Act: 4.3460. Min Act: -0.1700

Data Index: 812600 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 4.4397. Min Range: -4.4397

Max Act: 4.1272. Min Act: -0.1700

Data Index: 487603 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 4.4397. Min Range: -4.4397

Max Act: 4.0959. Min Act: -0.1700

Data Index: 125686 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 4.4397. Min Range: -4.4397

Max Act: 4.1584. Min Act: -0.1700

Data Index: 1277282 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 4.4397. Min Range: -4.4397

Max Act: 4.1272. Min Act: -0.1700

Data Index: 297176 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 4.4397. Min Range: -4.4397

Max Act: 4.0646. Min Act: -0.1700

Data Index: 231973 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 4.4397. Min Range: -4.4397

Max Act: 4.0646. Min Act: -0.1700

Data Index: 741255 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 4.4397. Min Range: -4.4397

Max Act: 4.0021. Min Act: -0.1700

Data Index: 546 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 4.4397. Min Range: -4.4397

Max Act: 4.0334. Min Act: -0.1700

Data Index: 513674 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 4.4397. Min Range: -4.4397

Max Act: 4.0021. Min Act: -0.1700

Data Index: 995894 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 4.4397. Min Range: -4.4397

Max Act: 3.9709. Min Act: -0.1700

Data Index: 1098759 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 4.4397. Min Range: -4.4397

Max Act: 3.9083. Min Act: -0.1700

Data Index: 621464 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 4.4397. Min Range: -4.4397

Max Act: 3.9396. Min Act: -0.1700

Data Index: 396950 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 4.4397. Min Range: -4.4397

Max Act: 3.9396. Min Act: -0.1700

Data Index: 216092 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 4.4397. Min Range: -4.4397

Max Act: 4.0646. Min Act: -0.1700

Data Index: 65528 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 4.4397. Min Range: -4.4397

Max Act: 3.9083. Min Act: -0.1700

Data Index: 847987 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 4.4397. Min Range: -4.4397

Max Act: 3.9396. Min Act: -0.1700

Data Index: 522465 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 4.4397. Min Range: -4.4397

Max Act: 3.9083. Min Act: -0.1700

Data Index: 769618 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 4.4397. Min Range: -4.4397

Max Act: 3.9396. Min Act: -0.1700

Data Index: 976369 (C4 (Web Text))

Max Activating Token Index: 781