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

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

Neuron 523 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: 5.5666. Min Range: -5.5666

Max Act: 5.5666. Min Act: -0.1700

Data Index: 1195358 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.5353. Min Act: -0.1700

Data Index: 6525 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.5353. Min Act: -0.1700

Data Index: 712683 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.4416. Min Act: -0.1700

Data Index: 823107 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.4103. Min Act: -0.1700

Data Index: 460003 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.4728. Min Act: -0.1700

Data Index: 872540 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.3791. Min Act: -0.1700

Data Index: 218357 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.3478. Min Act: -0.1700

Data Index: 925903 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.3166. Min Act: -0.1700

Data Index: 522163 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.2853. Min Act: -0.1700

Data Index: 249222 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.1916. Min Act: -0.1700

Data Index: 120640 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.2541. Min Act: -0.1700

Data Index: 557926 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.2853. Min Act: -0.1700

Data Index: 1174966 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.2541. Min Act: -0.1700

Data Index: 804498 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.2541. Min Act: -0.1700

Data Index: 699345 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.1916. Min Act: -0.1700

Data Index: 284705 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.1916. Min Act: -0.1700

Data Index: 545313 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.2541. Min Act: -0.1700

Data Index: 566669 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.1291. Min Act: -0.1700

Data Index: 799337 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.2228. Min Act: -0.1700

Data Index: 1117141 (C4 (Web Text))

Max Activating Token Index: 33