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

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

Neuron 1 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.7186. Min Act: -0.1700

Data Index: 1161655 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.6873. Min Act: -0.1700

Data Index: 32927 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.6247. Min Act: -0.1700

Data Index: 982412 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.6873. Min Act: -0.1700

Data Index: 1035746 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.6247. Min Act: -0.1700

Data Index: 545413 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.5934. Min Act: -0.1700

Data Index: 202571 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.5307. Min Act: -0.1700

Data Index: 54774 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.5307. Min Act: -0.1700

Data Index: 1067640 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.5620. Min Act: -0.1700

Data Index: 774274 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.5307. Min Act: -0.1700

Data Index: 1032086 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.5307. Min Act: -0.1700

Data Index: 146867 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.5620. Min Act: -0.1700

Data Index: 135557 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.5307. Min Act: -0.1700

Data Index: 650562 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.4994. Min Act: -0.1700

Data Index: 1187134 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.5620. Min Act: -0.1700

Data Index: 1012992 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.5307. Min Act: -0.1700

Data Index: 554663 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.4994. Min Act: -0.1700

Data Index: 1008874 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.4680. Min Act: -0.1700

Data Index: 505 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.4367. Min Act: -0.1700

Data Index: 149134 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.4367. Min Act: -0.1700

Data Index: 798247 (C4 (Web Text))

Max Activating Token Index: 481