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

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

Neuron 1330 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: 8.1796. Min Range: -8.1796

Max Act: 8.1796. Min Act: -0.1700

Data Index: 60510 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 8.1796. Min Range: -8.1796

Max Act: 7.9921. Min Act: -0.1700

Data Index: 1334216 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 8.1796. Min Range: -8.1796

Max Act: 8.0077. Min Act: -0.1700

Data Index: 1124841 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 8.1796. Min Range: -8.1796

Max Act: 7.8436. Min Act: -0.1700

Data Index: 127770 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 8.1796. Min Range: -8.1796

Max Act: 7.8046. Min Act: -0.1700

Data Index: 531796 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 8.1796. Min Range: -8.1796

Max Act: 7.7186. Min Act: -0.1700

Data Index: 1263463 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 8.1796. Min Range: -8.1796

Max Act: 7.7108. Min Act: -0.1700

Data Index: 1308482 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 8.1796. Min Range: -8.1796

Max Act: 7.6561. Min Act: -0.1700

Data Index: 547595 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 8.1796. Min Range: -8.1796

Max Act: 7.7343. Min Act: -0.1700

Data Index: 1236540 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 8.1796. Min Range: -8.1796

Max Act: 7.5546. Min Act: -0.1700

Data Index: 821266 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 8.1796. Min Range: -8.1796

Max Act: 7.6093. Min Act: -0.1700

Data Index: 1437707 (Python Code)

Max Activating Token Index: 1006

Text #11

Max Range: 8.1796. Min Range: -8.1796

Max Act: 7.6327. Min Act: -0.1700

Data Index: 1065605 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 8.1796. Min Range: -8.1796

Max Act: 7.6171. Min Act: -0.1700

Data Index: 927500 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 8.1796. Min Range: -8.1796

Max Act: 7.6249. Min Act: -0.1700

Data Index: 52513 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 8.1796. Min Range: -8.1796

Max Act: 7.5390. Min Act: -0.1700

Data Index: 468980 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 8.1796. Min Range: -8.1796

Max Act: 7.6093. Min Act: -0.1700

Data Index: 624288 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 8.1796. Min Range: -8.1796

Max Act: 7.5780. Min Act: -0.1700

Data Index: 304684 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 8.1796. Min Range: -8.1796

Max Act: 7.5780. Min Act: -0.1700

Data Index: 1077544 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 8.1796. Min Range: -8.1796

Max Act: 7.5468. Min Act: -0.1700

Data Index: 122247 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 8.1796. Min Range: -8.1796

Max Act: 7.5390. Min Act: -0.1700

Data Index: 328295 (C4 (Web Text))

Max Activating Token Index: 69