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

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

Neuron 373 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: 3.6920. Min Range: -3.6920

Max Act: 3.6920. Min Act: -0.1700

Data Index: 72382 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.6764. Min Act: -0.1700

Data Index: 1221334 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.6451. Min Act: -0.1700

Data Index: 428375 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.6294. Min Act: -0.1700

Data Index: 1237032 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.6451. Min Act: -0.1700

Data Index: 355935 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.6451. Min Act: -0.1700

Data Index: 53072 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.6607. Min Act: -0.1700

Data Index: 235623 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.6138. Min Act: -0.1700

Data Index: 43535 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.6294. Min Act: -0.1700

Data Index: 116930 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.6294. Min Act: -0.1700

Data Index: 1062916 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.6138. Min Act: -0.1700

Data Index: 559442 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.6294. Min Act: -0.1700

Data Index: 1081382 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.5981. Min Act: -0.1700

Data Index: 188242 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.5981. Min Act: -0.1700

Data Index: 160342 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.6138. Min Act: -0.1700

Data Index: 439232 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.6138. Min Act: -0.1700

Data Index: 1059171 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.5981. Min Act: -0.1700

Data Index: 100517 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.5825. Min Act: -0.1700

Data Index: 2413 (C4 (Web Text))

Max Activating Token Index: 856

Text #18

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.5981. Min Act: -0.1700

Data Index: 1015258 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.5981. Min Act: -0.1700

Data Index: 76965 (C4 (Web Text))

Max Activating Token Index: 850