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

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

Neuron 1651 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: 5.3154. Min Range: -5.3154

Max Act: 5.3154. Min Act: -0.1700

Data Index: 975052 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 5.3154. Min Range: -5.3154

Max Act: 5.1904. Min Act: -0.1700

Data Index: 762680 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 5.3154. Min Range: -5.3154

Max Act: 5.2529. Min Act: -0.1700

Data Index: 1220965 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 5.3154. Min Range: -5.3154

Max Act: 5.1904. Min Act: -0.1700

Data Index: 826309 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 5.3154. Min Range: -5.3154

Max Act: 5.1904. Min Act: -0.1700

Data Index: 339752 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 5.3154. Min Range: -5.3154

Max Act: 5.2216. Min Act: -0.1700

Data Index: 395435 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 5.3154. Min Range: -5.3154

Max Act: 5.1591. Min Act: -0.1700

Data Index: 1178353 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 5.3154. Min Range: -5.3154

Max Act: 5.1279. Min Act: -0.1700

Data Index: 793150 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 5.3154. Min Range: -5.3154

Max Act: 5.1279. Min Act: -0.1700

Data Index: 566995 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 5.3154. Min Range: -5.3154

Max Act: 5.1591. Min Act: -0.1700

Data Index: 1167613 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 5.3154. Min Range: -5.3154

Max Act: 5.1279. Min Act: -0.1700

Data Index: 375420 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 5.3154. Min Range: -5.3154

Max Act: 5.0966. Min Act: -0.1699

Data Index: 540482 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 5.3154. Min Range: -5.3154

Max Act: 5.0654. Min Act: -0.1700

Data Index: 1232552 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 5.3154. Min Range: -5.3154

Max Act: 5.1279. Min Act: -0.1700

Data Index: 147352 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 5.3154. Min Range: -5.3154

Max Act: 5.1591. Min Act: -0.1700

Data Index: 435203 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 5.3154. Min Range: -5.3154

Max Act: 5.1279. Min Act: -0.1700

Data Index: 790640 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 5.3154. Min Range: -5.3154

Max Act: 5.0966. Min Act: -0.1700

Data Index: 603275 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 5.3154. Min Range: -5.3154

Max Act: 5.0654. Min Act: -0.1700

Data Index: 1190521 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 5.3154. Min Range: -5.3154

Max Act: 5.0966. Min Act: -0.1700

Data Index: 988810 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 5.3154. Min Range: -5.3154

Max Act: 5.0341. Min Act: -0.1700

Data Index: 35292 (C4 (Web Text))

Max Activating Token Index: 69