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

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

Neuron 63 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: 5.7865. Min Range: -5.7865

Max Act: 5.7865. Min Act: -0.1700

Data Index: 1319959 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.7865. Min Act: -0.1700

Data Index: 167112 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.7240. Min Act: -0.1700

Data Index: 1078335 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.7240. Min Act: -0.1700

Data Index: 801311 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.6927. Min Act: -0.1700

Data Index: 794209 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.6615. Min Act: -0.1700

Data Index: 1220852 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.6615. Min Act: -0.1700

Data Index: 541308 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.6302. Min Act: -0.1700

Data Index: 919461 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.6615. Min Act: -0.1700

Data Index: 981407 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.5990. Min Act: -0.1700

Data Index: 4035 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.5990. Min Act: -0.1700

Data Index: 769764 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.5677. Min Act: -0.1700

Data Index: 328866 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.5052. Min Act: -0.1700

Data Index: 1024384 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.5365. Min Act: -0.1700

Data Index: 375906 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.5365. Min Act: -0.1700

Data Index: 395863 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.5365. Min Act: -0.1700

Data Index: 401844 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.4740. Min Act: -0.1700

Data Index: 1149987 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.4740. Min Act: -0.1700

Data Index: 1151901 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.5052. Min Act: -0.1700

Data Index: 295996 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.4427. Min Act: -0.1700

Data Index: 497764 (C4 (Web Text))

Max Activating Token Index: 275