Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 828 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.5443. Min Range: -4.5443

Max Act: 4.5443. Min Act: -0.1700

Data Index: 988859 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 4.5443. Min Range: -4.5443

Max Act: 4.0153. Min Act: -0.1700

Data Index: 222659 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 4.5443. Min Range: -4.5443

Max Act: 4.0459. Min Act: -0.1700

Data Index: 388717 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 4.5443. Min Range: -4.5443

Max Act: 4.0319. Min Act: -0.1700

Data Index: 1045246 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 4.5443. Min Range: -4.5443

Max Act: 3.9989. Min Act: -0.1700

Data Index: 863139 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 4.5443. Min Range: -4.5443

Max Act: 4.0023. Min Act: -0.1700

Data Index: 45759 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 4.5443. Min Range: -4.5443

Max Act: 3.9794. Min Act: -0.1700

Data Index: 488779 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 4.5443. Min Range: -4.5443

Max Act: 3.9629. Min Act: -0.1700

Data Index: 444858 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 4.5443. Min Range: -4.5443

Max Act: 3.9607. Min Act: -0.1700

Data Index: 504200 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 4.5443. Min Range: -4.5443

Max Act: 3.9703. Min Act: -0.1700

Data Index: 709696 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 4.5443. Min Range: -4.5443

Max Act: 3.9935. Min Act: -0.1700

Data Index: 309740 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 4.5443. Min Range: -4.5443

Max Act: 3.9448. Min Act: -0.1700

Data Index: 1415876 (Python Code)

Max Activating Token Index: 1021

Text #12

Max Range: 4.5443. Min Range: -4.5443

Max Act: 3.9387. Min Act: -0.1700

Data Index: 198084 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 4.5443. Min Range: -4.5443

Max Act: 3.9478. Min Act: -0.1700

Data Index: 182396 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 4.5443. Min Range: -4.5443

Max Act: 3.9471. Min Act: -0.1700

Data Index: 473133 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 4.5443. Min Range: -4.5443

Max Act: 3.9031. Min Act: -0.1700

Data Index: 907780 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 4.5443. Min Range: -4.5443

Max Act: 3.8995. Min Act: -0.1700

Data Index: 825075 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 4.5443. Min Range: -4.5443

Max Act: 3.8916. Min Act: -0.1700

Data Index: 1024160 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 4.5443. Min Range: -4.5443

Max Act: 3.9306. Min Act: -0.1700

Data Index: 348524 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 4.5443. Min Range: -4.5443

Max Act: 3.8731. Min Act: -0.1700

Data Index: 1033389 (C4 (Web Text))

Max Activating Token Index: 438