Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 676 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.6175. Min Act: -0.1699

Data Index: 923964 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.5863. Min Act: -0.1699

Data Index: 1112865 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.6175. Min Act: -0.1699

Data Index: 1353811 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.6175. Min Act: -0.1700

Data Index: 19249 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.5863. Min Act: -0.1699

Data Index: 883916 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.4300. Min Act: -0.1698

Data Index: 110253 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.4925. Min Act: -0.1700

Data Index: 1325379 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.4300. Min Act: -0.1697

Data Index: 1281486 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.3675. Min Act: -0.1700

Data Index: 334041 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.3675. Min Act: -0.1699

Data Index: 116894 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.3363. Min Act: -0.1699

Data Index: 405120 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.3050. Min Act: -0.1699

Data Index: 172163 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.3988. Min Act: -0.1700

Data Index: 606157 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.3675. Min Act: -0.1700

Data Index: 1286735 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.3050. Min Act: -0.1700

Data Index: 99122 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.3050. Min Act: -0.1699

Data Index: 546252 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.3363. Min Act: -0.1700

Data Index: 85832 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.2425. Min Act: -0.1699

Data Index: 299618 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.2738. Min Act: -0.1700

Data Index: 979206 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.2738. Min Act: -0.1700

Data Index: 220275 (C4 (Web Text))

Max Activating Token Index: 203