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

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

Neuron 211 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: 3.8352. Min Range: -3.8352

Max Act: 3.8039. Min Act: -0.1700

Data Index: 696019 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.8352. Min Act: -0.1700

Data Index: 865243 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.7413. Min Act: -0.1700

Data Index: 343838 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.7726. Min Act: -0.1700

Data Index: 836192 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.7100. Min Act: -0.1700

Data Index: 736367 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.6787. Min Act: -0.1700

Data Index: 476182 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.7726. Min Act: -0.1700

Data Index: 904935 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.7100. Min Act: -0.1700

Data Index: 1066605 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.6787. Min Act: -0.1700

Data Index: 742440 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.6161. Min Act: -0.1700

Data Index: 925854 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.7413. Min Act: -0.1700

Data Index: 731645 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.6787. Min Act: -0.1700

Data Index: 81346 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.6474. Min Act: -0.1700

Data Index: 265249 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.7100. Min Act: -0.1700

Data Index: 1273274 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.6787. Min Act: -0.1700

Data Index: 387278 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.6787. Min Act: -0.1700

Data Index: 770066 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.6474. Min Act: -0.1700

Data Index: 375084 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.6474. Min Act: -0.1700

Data Index: 540991 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.6474. Min Act: -0.1700

Data Index: 518946 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.6787. Min Act: -0.1700

Data Index: 153262 (C4 (Web Text))

Max Activating Token Index: 926