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

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

Neuron 1260 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: 3.5268. Min Range: -3.5268

Max Act: 3.5268. Min Act: -0.1700

Data Index: 1256545 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 3.5268. Min Range: -3.5268

Max Act: 3.3857. Min Act: -0.1700

Data Index: 1312903 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 3.5268. Min Range: -3.5268

Max Act: 3.3700. Min Act: -0.1700

Data Index: 402023 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 3.5268. Min Range: -3.5268

Max Act: 3.3857. Min Act: -0.1700

Data Index: 808125 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.5268. Min Range: -3.5268

Max Act: 3.3229. Min Act: -0.1700

Data Index: 931873 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.5268. Min Range: -3.5268

Max Act: 3.3072. Min Act: -0.1700

Data Index: 998782 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 3.5268. Min Range: -3.5268

Max Act: 3.2915. Min Act: -0.1700

Data Index: 1334126 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 3.5268. Min Range: -3.5268

Max Act: 3.2758. Min Act: -0.1700

Data Index: 642553 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 3.5268. Min Range: -3.5268

Max Act: 3.2601. Min Act: -0.1700

Data Index: 655190 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 3.5268. Min Range: -3.5268

Max Act: 3.2443. Min Act: -0.1700

Data Index: 1231314 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 3.5268. Min Range: -3.5268

Max Act: 3.2601. Min Act: -0.1700

Data Index: 844724 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 3.5268. Min Range: -3.5268

Max Act: 3.2915. Min Act: -0.1700

Data Index: 622202 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.5268. Min Range: -3.5268

Max Act: 3.2758. Min Act: -0.1700

Data Index: 909205 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 3.5268. Min Range: -3.5268

Max Act: 3.2443. Min Act: -0.1700

Data Index: 688769 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 3.5268. Min Range: -3.5268

Max Act: 3.2758. Min Act: -0.1700

Data Index: 1127634 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 3.5268. Min Range: -3.5268

Max Act: 3.2601. Min Act: -0.1700

Data Index: 500606 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 3.5268. Min Range: -3.5268

Max Act: 3.2443. Min Act: -0.1700

Data Index: 442249 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 3.5268. Min Range: -3.5268

Max Act: 3.2443. Min Act: -0.1700

Data Index: 1083847 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 3.5268. Min Range: -3.5268

Max Act: 3.2129. Min Act: -0.1700

Data Index: 310125 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 3.5268. Min Range: -3.5268

Max Act: 3.2286. Min Act: -0.1700

Data Index: 620690 (C4 (Web Text))

Max Activating Token Index: 552