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

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

Neuron 72 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.2265. Min Act: -0.1700

Data Index: 219334 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.1636. Min Act: -0.1700

Data Index: 514282 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.1636. Min Act: -0.1700

Data Index: 651592 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.1636. Min Act: -0.1700

Data Index: 581224 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.1163. Min Act: -0.1700

Data Index: 46288 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.1163. Min Act: -0.1700

Data Index: 752680 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.0848. Min Act: -0.1700

Data Index: 1148941 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.1005. Min Act: -0.1700

Data Index: 107187 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.1005. Min Act: -0.1700

Data Index: 267863 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.0690. Min Act: -0.1700

Data Index: 665266 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.0690. Min Act: -0.1700

Data Index: 703062 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.0848. Min Act: -0.1700

Data Index: 833168 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.1321. Min Act: -0.1700

Data Index: 130272 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.0690. Min Act: -0.1700

Data Index: 1028364 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.0690. Min Act: -0.1700

Data Index: 1258221 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.0532. Min Act: -0.1700

Data Index: 878665 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.0374. Min Act: -0.1700

Data Index: 790570 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.0532. Min Act: -0.1700

Data Index: 247018 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.0532. Min Act: -0.1700

Data Index: 157943 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.0532. Min Act: -0.1700

Data Index: 285289 (C4 (Web Text))

Max Activating Token Index: 50