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

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

Neuron 1474 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.3978. Min Act: -0.1700

Data Index: 1342287 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.3821. Min Act: -0.1700

Data Index: 970004 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.3193. Min Act: -0.1700

Data Index: 177917 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.2722. Min Act: -0.1700

Data Index: 1004708 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.2250. Min Act: -0.1700

Data Index: 139211 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.1936. Min Act: -0.1700

Data Index: 965865 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.1936. Min Act: -0.1700

Data Index: 811253 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.1464. Min Act: -0.1700

Data Index: 255254 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.1306. Min Act: -0.1700

Data Index: 646205 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.1148. Min Act: -0.1700

Data Index: 1169293 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.1148. Min Act: -0.1700

Data Index: 643451 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.1148. Min Act: -0.1700

Data Index: 748897 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.1148. Min Act: -0.1700

Data Index: 1280270 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.0991. Min Act: -0.1700

Data Index: 264949 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.1148. Min Act: -0.1700

Data Index: 1210809 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.0675. Min Act: -0.1700

Data Index: 391745 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.0833. Min Act: -0.1700

Data Index: 1002577 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.0991. Min Act: -0.1700

Data Index: 783250 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.0991. Min Act: -0.1700

Data Index: 847275 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.0833. Min Act: -0.1700

Data Index: 640490 (C4 (Web Text))

Max Activating Token Index: 25