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

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

Neuron 557 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: 15.3397. Min Range: -15.3397

Max Act: 15.3397. Min Act: -0.1699

Data Index: 351424 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 15.3397. Min Range: -15.3397

Max Act: 15.0272. Min Act: -0.1699

Data Index: 1130398 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 15.3397. Min Range: -15.3397

Max Act: 14.7772. Min Act: -0.1700

Data Index: 490140 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 15.3397. Min Range: -15.3397

Max Act: 14.6522. Min Act: -0.1699

Data Index: 880202 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 15.3397. Min Range: -15.3397

Max Act: 14.7147. Min Act: -0.1700

Data Index: 657583 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 15.3397. Min Range: -15.3397

Max Act: 14.3397. Min Act: -0.1700

Data Index: 615099 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 15.3397. Min Range: -15.3397

Max Act: 14.4022. Min Act: -0.1700

Data Index: 1135385 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 15.3397. Min Range: -15.3397

Max Act: 14.2147. Min Act: -0.1700

Data Index: 1305859 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 15.3397. Min Range: -15.3397

Max Act: 14.2147. Min Act: -0.1700

Data Index: 559366 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 15.3397. Min Range: -15.3397

Max Act: 14.0897. Min Act: -0.1700

Data Index: 1252860 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 15.3397. Min Range: -15.3397

Max Act: 14.0272. Min Act: -0.1695

Data Index: 479436 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 15.3397. Min Range: -15.3397

Max Act: 13.9647. Min Act: -0.1698

Data Index: 645664 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 15.3397. Min Range: -15.3397

Max Act: 13.8397. Min Act: -0.1700

Data Index: 345745 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 15.3397. Min Range: -15.3397

Max Act: 13.7772. Min Act: -0.1697

Data Index: 1279207 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 15.3397. Min Range: -15.3397

Max Act: 13.7147. Min Act: -0.1700

Data Index: 669645 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 15.3397. Min Range: -15.3397

Max Act: 13.9647. Min Act: -0.1700

Data Index: 254163 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 15.3397. Min Range: -15.3397

Max Act: 13.8397. Min Act: -0.1700

Data Index: 437999 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 15.3397. Min Range: -15.3397

Max Act: 13.9022. Min Act: -0.1700

Data Index: 1335959 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 15.3397. Min Range: -15.3397

Max Act: 13.8397. Min Act: -0.1700

Data Index: 1007791 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 15.3397. Min Range: -15.3397

Max Act: 13.6522. Min Act: -0.1700

Data Index: 42315 (C4 (Web Text))

Max Activating Token Index: 397