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

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

Neuron 834 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: 5.7682. Min Range: -5.7682

Max Act: 5.7682. Min Act: -0.1700

Data Index: 887600 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.6432. Min Act: -0.1697

Data Index: 496287 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.6119. Min Act: -0.1700

Data Index: 391240 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.6119. Min Act: -0.1700

Data Index: 1219137 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.5494. Min Act: -0.1700

Data Index: 1276446 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.5494. Min Act: -0.1700

Data Index: 1165630 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.5182. Min Act: -0.1699

Data Index: 523144 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.4557. Min Act: -0.1700

Data Index: 601387 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.4244. Min Act: -0.1700

Data Index: 69019 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.4244. Min Act: -0.1700

Data Index: 1306929 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.4244. Min Act: -0.1700

Data Index: 645814 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.3932. Min Act: -0.1700

Data Index: 373307 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.4244. Min Act: -0.1700

Data Index: 1345955 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.4244. Min Act: -0.1700

Data Index: 809161 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.3932. Min Act: -0.1700

Data Index: 597146 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.3619. Min Act: -0.1700

Data Index: 435533 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.3619. Min Act: -0.1697

Data Index: 420458 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.3619. Min Act: -0.1699

Data Index: 1264771 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.4557. Min Act: -0.1700

Data Index: 247199 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.3932. Min Act: -0.1700

Data Index: 1137364 (C4 (Web Text))

Max Activating Token Index: 110