Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 602 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.2968. Min Range: -5.2968

Max Act: 5.2968. Min Act: -0.1700

Data Index: 791004 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 5.2968. Min Range: -5.2968

Max Act: 5.1405. Min Act: -0.1700

Data Index: 451197 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 5.2968. Min Range: -5.2968

Max Act: 5.0468. Min Act: -0.1700

Data Index: 569198 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 5.2968. Min Range: -5.2968

Max Act: 5.0468. Min Act: -0.1700

Data Index: 1134701 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 5.2968. Min Range: -5.2968

Max Act: 4.9843. Min Act: -0.1700

Data Index: 565429 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 5.2968. Min Range: -5.2968

Max Act: 5.0155. Min Act: -0.1700

Data Index: 197937 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 5.2968. Min Range: -5.2968

Max Act: 4.9843. Min Act: -0.1700

Data Index: 661449 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 5.2968. Min Range: -5.2968

Max Act: 4.9843. Min Act: -0.1700

Data Index: 295804 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 5.2968. Min Range: -5.2968

Max Act: 4.9218. Min Act: -0.1700

Data Index: 399258 (C4 (Web Text))

Max Activating Token Index: 818

Text #9

Max Range: 5.2968. Min Range: -5.2968

Max Act: 4.9530. Min Act: -0.1700

Data Index: 422245 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 5.2968. Min Range: -5.2968

Max Act: 4.9218. Min Act: -0.1700

Data Index: 372535 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 5.2968. Min Range: -5.2968

Max Act: 4.8593. Min Act: -0.1700

Data Index: 1280702 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 5.2968. Min Range: -5.2968

Max Act: 4.8905. Min Act: -0.1700

Data Index: 663193 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 5.2968. Min Range: -5.2968

Max Act: 4.9218. Min Act: -0.1700

Data Index: 442286 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 5.2968. Min Range: -5.2968

Max Act: 4.8905. Min Act: -0.1700

Data Index: 844851 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 5.2968. Min Range: -5.2968

Max Act: 4.7968. Min Act: -0.1700

Data Index: 599660 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 5.2968. Min Range: -5.2968

Max Act: 4.8280. Min Act: -0.1700

Data Index: 37586 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 5.2968. Min Range: -5.2968

Max Act: 4.7968. Min Act: -0.1700

Data Index: 260325 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 5.2968. Min Range: -5.2968

Max Act: 4.7968. Min Act: -0.1700

Data Index: 1190891 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 5.2968. Min Range: -5.2968

Max Act: 4.8280. Min Act: -0.1700

Data Index: 84684 (C4 (Web Text))

Max Activating Token Index: 871