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

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

Neuron 87 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: 3.1684. Min Range: -3.1684

Max Act: 3.1684. Min Act: -0.1700

Data Index: 367671 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 3.1684. Min Range: -3.1684

Max Act: 3.1369. Min Act: -0.1700

Data Index: 723116 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 3.1684. Min Range: -3.1684

Max Act: 3.1212. Min Act: -0.1700

Data Index: 484712 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 3.1684. Min Range: -3.1684

Max Act: 3.1212. Min Act: -0.1700

Data Index: 799433 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 3.1684. Min Range: -3.1684

Max Act: 3.1212. Min Act: -0.1700

Data Index: 854939 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 3.1684. Min Range: -3.1684

Max Act: 3.0739. Min Act: -0.1700

Data Index: 1069211 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 3.1684. Min Range: -3.1684

Max Act: 3.0581. Min Act: -0.1700

Data Index: 772471 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 3.1684. Min Range: -3.1684

Max Act: 3.0739. Min Act: -0.1700

Data Index: 779928 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 3.1684. Min Range: -3.1684

Max Act: 3.0423. Min Act: -0.1700

Data Index: 690796 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 3.1684. Min Range: -3.1684

Max Act: 3.0265. Min Act: -0.1700

Data Index: 1042126 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 3.1684. Min Range: -3.1684

Max Act: 3.0265. Min Act: -0.1700

Data Index: 895255 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 3.1684. Min Range: -3.1684

Max Act: 3.0423. Min Act: -0.1700

Data Index: 721076 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 3.1684. Min Range: -3.1684

Max Act: 3.0423. Min Act: -0.1700

Data Index: 1025468 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 3.1684. Min Range: -3.1684

Max Act: 2.9949. Min Act: -0.1700

Data Index: 379063 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 3.1684. Min Range: -3.1684

Max Act: 3.0265. Min Act: -0.1700

Data Index: 729152 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 3.1684. Min Range: -3.1684

Max Act: 2.9791. Min Act: -0.1700

Data Index: 1321200 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 3.1684. Min Range: -3.1684

Max Act: 3.0107. Min Act: -0.1700

Data Index: 905025 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 3.1684. Min Range: -3.1684

Max Act: 3.0107. Min Act: -0.1700

Data Index: 1334034 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 3.1684. Min Range: -3.1684

Max Act: 3.0265. Min Act: -0.1700

Data Index: 593051 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 3.1684. Min Range: -3.1684

Max Act: 2.9791. Min Act: -0.1700

Data Index: 938487 (C4 (Web Text))

Max Activating Token Index: 94