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

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

Neuron 836 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.8045. Min Range: -5.8045

Max Act: 5.8045. Min Act: -0.1700

Data Index: 1314322 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 5.8045. Min Range: -5.8045

Max Act: 5.7420. Min Act: -0.1700

Data Index: 1111546 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 5.8045. Min Range: -5.8045

Max Act: 5.6482. Min Act: -0.1700

Data Index: 872841 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 5.8045. Min Range: -5.8045

Max Act: 5.6170. Min Act: -0.1700

Data Index: 1026605 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 5.8045. Min Range: -5.8045

Max Act: 5.5857. Min Act: -0.1700

Data Index: 620445 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 5.8045. Min Range: -5.8045

Max Act: 5.5545. Min Act: -0.1700

Data Index: 661356 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 5.8045. Min Range: -5.8045

Max Act: 5.4920. Min Act: -0.1700

Data Index: 1093174 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 5.8045. Min Range: -5.8045

Max Act: 5.4920. Min Act: -0.1700

Data Index: 412748 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 5.8045. Min Range: -5.8045

Max Act: 5.4920. Min Act: -0.1700

Data Index: 1230816 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 5.8045. Min Range: -5.8045

Max Act: 5.4607. Min Act: -0.1700

Data Index: 1163884 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 5.8045. Min Range: -5.8045

Max Act: 5.4295. Min Act: -0.1700

Data Index: 710261 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 5.8045. Min Range: -5.8045

Max Act: 5.3982. Min Act: -0.1700

Data Index: 1209765 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 5.8045. Min Range: -5.8045

Max Act: 5.3357. Min Act: -0.1700

Data Index: 413714 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 5.8045. Min Range: -5.8045

Max Act: 5.3670. Min Act: -0.1700

Data Index: 232812 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 5.8045. Min Range: -5.8045

Max Act: 5.3670. Min Act: -0.1700

Data Index: 868081 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 5.8045. Min Range: -5.8045

Max Act: 5.3670. Min Act: -0.1700

Data Index: 50323 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 5.8045. Min Range: -5.8045

Max Act: 5.3670. Min Act: -0.1700

Data Index: 796685 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 5.8045. Min Range: -5.8045

Max Act: 5.3045. Min Act: -0.1700

Data Index: 142151 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 5.8045. Min Range: -5.8045

Max Act: 5.3045. Min Act: -0.1700

Data Index: 311432 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 5.8045. Min Range: -5.8045

Max Act: 5.2420. Min Act: -0.1700

Data Index: 254727 (C4 (Web Text))

Max Activating Token Index: 306