Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1050 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.9320. Min Range: -5.9320

Max Act: 5.9320. Min Act: -0.1700

Data Index: 1199381 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 5.9320. Min Range: -5.9320

Max Act: 5.9320. Min Act: -0.1700

Data Index: 1250610 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 5.9320. Min Range: -5.9320

Max Act: 5.8382. Min Act: -0.1700

Data Index: 1052396 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 5.9320. Min Range: -5.9320

Max Act: 5.7757. Min Act: -0.1700

Data Index: 71504 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 5.9320. Min Range: -5.9320

Max Act: 5.7132. Min Act: -0.1700

Data Index: 714698 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 5.9320. Min Range: -5.9320

Max Act: 5.7757. Min Act: -0.1700

Data Index: 1320993 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 5.9320. Min Range: -5.9320

Max Act: 5.7132. Min Act: -0.1700

Data Index: 885645 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 5.9320. Min Range: -5.9320

Max Act: 5.6820. Min Act: -0.1700

Data Index: 794360 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 5.9320. Min Range: -5.9320

Max Act: 5.6820. Min Act: -0.1700

Data Index: 434192 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 5.9320. Min Range: -5.9320

Max Act: 5.6195. Min Act: -0.1700

Data Index: 476266 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 5.9320. Min Range: -5.9320

Max Act: 5.5882. Min Act: -0.1700

Data Index: 106193 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 5.9320. Min Range: -5.9320

Max Act: 5.6507. Min Act: -0.1700

Data Index: 689692 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 5.9320. Min Range: -5.9320

Max Act: 5.6195. Min Act: -0.1700

Data Index: 1132744 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 5.9320. Min Range: -5.9320

Max Act: 5.5570. Min Act: -0.1700

Data Index: 571378 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 5.9320. Min Range: -5.9320

Max Act: 5.5882. Min Act: -0.1700

Data Index: 238503 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 5.9320. Min Range: -5.9320

Max Act: 5.5882. Min Act: -0.1700

Data Index: 937130 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 5.9320. Min Range: -5.9320

Max Act: 5.5882. Min Act: -0.1700

Data Index: 1228981 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 5.9320. Min Range: -5.9320

Max Act: 5.6195. Min Act: -0.1700

Data Index: 848949 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 5.9320. Min Range: -5.9320

Max Act: 5.4945. Min Act: -0.1700

Data Index: 274344 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 5.9320. Min Range: -5.9320

Max Act: 5.5882. Min Act: -0.1700

Data Index: 537777 (C4 (Web Text))

Max Activating Token Index: 689