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

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

Neuron 126 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: 3.8200. Min Range: -3.8200

Max Act: 3.8200. Min Act: -0.1700

Data Index: 235216 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.7887. Min Act: -0.1700

Data Index: 1335426 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.7887. Min Act: -0.1700

Data Index: 303298 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.7887. Min Act: -0.1700

Data Index: 204308 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.7574. Min Act: -0.1700

Data Index: 336659 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.7574. Min Act: -0.1700

Data Index: 1133330 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.7574. Min Act: -0.1700

Data Index: 51219 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.7261. Min Act: -0.1700

Data Index: 1188500 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.7261. Min Act: -0.1700

Data Index: 1145103 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.7261. Min Act: -0.1700

Data Index: 729222 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.6949. Min Act: -0.1700

Data Index: 477824 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.7261. Min Act: -0.1700

Data Index: 793425 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.6636. Min Act: -0.1700

Data Index: 708360 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.6636. Min Act: -0.1700

Data Index: 908565 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.7261. Min Act: -0.1700

Data Index: 537760 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.6636. Min Act: -0.1700

Data Index: 958068 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.6636. Min Act: -0.1700

Data Index: 1111489 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.6636. Min Act: -0.1700

Data Index: 940312 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.6636. Min Act: -0.1700

Data Index: 1135710 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.6636. Min Act: -0.1700

Data Index: 419423 (C4 (Web Text))

Max Activating Token Index: 927