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

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

Neuron 1083 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.3671. Min Act: -0.1700

Data Index: 1110716 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.3200. Min Act: -0.1700

Data Index: 798023 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.3200. Min Act: -0.1700

Data Index: 356797 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.2886. Min Act: -0.1700

Data Index: 438194 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.2886. Min Act: -0.1700

Data Index: 663020 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.2729. Min Act: -0.1700

Data Index: 1257469 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.2572. Min Act: -0.1700

Data Index: 848916 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.2572. Min Act: -0.1700

Data Index: 587575 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.2729. Min Act: -0.1700

Data Index: 535622 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.2414. Min Act: -0.1700

Data Index: 441319 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.2414. Min Act: -0.1700

Data Index: 955637 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.2100. Min Act: -0.1700

Data Index: 441133 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.2414. Min Act: -0.1700

Data Index: 93201 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.2257. Min Act: -0.1700

Data Index: 530158 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.1943. Min Act: -0.1700

Data Index: 1359553 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.2257. Min Act: -0.1700

Data Index: 470368 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.2414. Min Act: -0.1700

Data Index: 1279241 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.2100. Min Act: -0.1700

Data Index: 610314 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.2257. Min Act: -0.1700

Data Index: 1187694 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.1785. Min Act: -0.1700

Data Index: 765954 (C4 (Web Text))

Max Activating Token Index: 322