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

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

Neuron 1059 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.7749. Min Act: -0.1700

Data Index: 124845 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.7436. Min Act: -0.1700

Data Index: 1156174 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.7436. Min Act: -0.1700

Data Index: 629280 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.7436. Min Act: -0.1700

Data Index: 1335335 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.7436. Min Act: -0.1700

Data Index: 1204582 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.6811. Min Act: -0.1700

Data Index: 65341 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.6499. Min Act: -0.1700

Data Index: 326740 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.6186. Min Act: -0.1700

Data Index: 205323 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.6499. Min Act: -0.1700

Data Index: 666245 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.6186. Min Act: -0.1700

Data Index: 692014 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.6186. Min Act: -0.1700

Data Index: 916598 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.6186. Min Act: -0.1700

Data Index: 1079487 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.5561. Min Act: -0.1700

Data Index: 653044 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.5249. Min Act: -0.1700

Data Index: 99411 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.6186. Min Act: -0.1700

Data Index: 104467 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.5249. Min Act: -0.1700

Data Index: 900220 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.5249. Min Act: -0.1700

Data Index: 765209 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.4936. Min Act: -0.1700

Data Index: 236986 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.4936. Min Act: -0.1700

Data Index: 514427 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.4624. Min Act: -0.1700

Data Index: 917505 (C4 (Web Text))

Max Activating Token Index: 700