Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 886 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.9743. Min Range: -3.9743

Max Act: 3.9743. Min Act: -0.1700

Data Index: 511424 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 3.9743. Min Range: -3.9743

Max Act: 3.7866. Min Act: -0.1700

Data Index: 1330031 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 3.9743. Min Range: -3.9743

Max Act: 3.7553. Min Act: -0.1700

Data Index: 646588 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 3.9743. Min Range: -3.9743

Max Act: 3.6928. Min Act: -0.1700

Data Index: 402501 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 3.9743. Min Range: -3.9743

Max Act: 3.7084. Min Act: -0.1700

Data Index: 1349352 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 3.9743. Min Range: -3.9743

Max Act: 3.7084. Min Act: -0.1700

Data Index: 134162 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 3.9743. Min Range: -3.9743

Max Act: 3.6145. Min Act: -0.1700

Data Index: 446854 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 3.9743. Min Range: -3.9743

Max Act: 3.5675. Min Act: -0.1700

Data Index: 1005903 (C4 (Web Text))

Max Activating Token Index: 448

Text #8

Max Range: 3.9743. Min Range: -3.9743

Max Act: 3.5988. Min Act: -0.1700

Data Index: 1006686 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 3.9743. Min Range: -3.9743

Max Act: 3.5519. Min Act: -0.1700

Data Index: 1271388 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 3.9743. Min Range: -3.9743

Max Act: 3.5519. Min Act: -0.1700

Data Index: 444043 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 3.9743. Min Range: -3.9743

Max Act: 3.5675. Min Act: -0.1700

Data Index: 448547 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 3.9743. Min Range: -3.9743

Max Act: 3.5675. Min Act: -0.1700

Data Index: 82418 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 3.9743. Min Range: -3.9743

Max Act: 3.5362. Min Act: -0.1700

Data Index: 533848 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 3.9743. Min Range: -3.9743

Max Act: 3.5988. Min Act: -0.1700

Data Index: 1194667 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 3.9743. Min Range: -3.9743

Max Act: 3.5519. Min Act: -0.1700

Data Index: 1110609 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 3.9743. Min Range: -3.9743

Max Act: 3.5362. Min Act: -0.1700

Data Index: 751843 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 3.9743. Min Range: -3.9743

Max Act: 3.5362. Min Act: -0.1700

Data Index: 183679 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 3.9743. Min Range: -3.9743

Max Act: 3.5049. Min Act: -0.1700

Data Index: 564025 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 3.9743. Min Range: -3.9743

Max Act: 3.5519. Min Act: -0.1700

Data Index: 947173 (C4 (Web Text))

Max Activating Token Index: 331