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

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

Neuron 1210 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: 3.8198. Min Range: -3.8198

Max Act: 3.8198. Min Act: -0.1700

Data Index: 922824 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.7572. Min Act: -0.1700

Data Index: 858855 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.7572. Min Act: -0.1700

Data Index: 212761 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.6946. Min Act: -0.1700

Data Index: 661094 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.6320. Min Act: -0.1700

Data Index: 1128576 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.6320. Min Act: -0.1700

Data Index: 1189016 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.6320. Min Act: -0.1700

Data Index: 570503 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.6633. Min Act: -0.1700

Data Index: 1233825 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.6320. Min Act: -0.1700

Data Index: 130102 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.6007. Min Act: -0.1700

Data Index: 242702 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.5851. Min Act: -0.1700

Data Index: 795649 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.5694. Min Act: -0.1700

Data Index: 1122910 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.5537. Min Act: -0.1700

Data Index: 809201 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.5381. Min Act: -0.1700

Data Index: 984038 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.5694. Min Act: -0.1700

Data Index: 939062 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.5537. Min Act: -0.1700

Data Index: 557009 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.5381. Min Act: -0.1700

Data Index: 1357604 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.5537. Min Act: -0.1700

Data Index: 364730 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.5537. Min Act: -0.1700

Data Index: 22734 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.5381. Min Act: -0.1700

Data Index: 3791 (C4 (Web Text))

Max Activating Token Index: 825