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

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

Neuron 1237 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7757. Min Range: -3.7757

Max Act: 3.7757. Min Act: -0.1700

Data Index: 1130782 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 3.7757. Min Range: -3.7757

Max Act: 3.6348. Min Act: -0.1700

Data Index: 649991 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 3.7757. Min Range: -3.7757

Max Act: 3.5879. Min Act: -0.1700

Data Index: 1097454 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 3.7757. Min Range: -3.7757

Max Act: 3.5565. Min Act: -0.1700

Data Index: 1322516 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 3.7757. Min Range: -3.7757

Max Act: 3.4939. Min Act: -0.1700

Data Index: 494784 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 3.7757. Min Range: -3.7757

Max Act: 3.4939. Min Act: -0.1700

Data Index: 934649 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 3.7757. Min Range: -3.7757

Max Act: 3.4939. Min Act: -0.1700

Data Index: 1057138 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 3.7757. Min Range: -3.7757

Max Act: 3.4782. Min Act: -0.1700

Data Index: 602172 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 3.7757. Min Range: -3.7757

Max Act: 3.4782. Min Act: -0.1700

Data Index: 324093 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 3.7757. Min Range: -3.7757

Max Act: 3.4469. Min Act: -0.1700

Data Index: 162842 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 3.7757. Min Range: -3.7757

Max Act: 3.4469. Min Act: -0.1700

Data Index: 808443 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 3.7757. Min Range: -3.7757

Max Act: 3.4469. Min Act: -0.1700

Data Index: 503066 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 3.7757. Min Range: -3.7757

Max Act: 3.4312. Min Act: -0.1700

Data Index: 628417 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 3.7757. Min Range: -3.7757

Max Act: 3.4312. Min Act: -0.1700

Data Index: 1129793 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 3.7757. Min Range: -3.7757

Max Act: 3.4469. Min Act: -0.1700

Data Index: 338662 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 3.7757. Min Range: -3.7757

Max Act: 3.4312. Min Act: -0.1700

Data Index: 237867 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 3.7757. Min Range: -3.7757

Max Act: 3.3841. Min Act: -0.1700

Data Index: 458672 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 3.7757. Min Range: -3.7757

Max Act: 3.4155. Min Act: -0.1700

Data Index: 1292812 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 3.7757. Min Range: -3.7757

Max Act: 3.3998. Min Act: -0.1700

Data Index: 443070 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 3.7757. Min Range: -3.7757

Max Act: 3.3998. Min Act: -0.1700

Data Index: 896766 (C4 (Web Text))

Max Activating Token Index: 950