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

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

Neuron 1768 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: 5.7289. Min Range: -5.7289

Max Act: 5.7289. Min Act: -0.1700

Data Index: 854913 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 5.7289. Min Range: -5.7289

Max Act: 5.6977. Min Act: -0.1700

Data Index: 1168026 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 5.7289. Min Range: -5.7289

Max Act: 5.7289. Min Act: -0.1700

Data Index: 782467 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 5.7289. Min Range: -5.7289

Max Act: 5.6664. Min Act: -0.1700

Data Index: 483031 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 5.7289. Min Range: -5.7289

Max Act: 5.6664. Min Act: -0.1700

Data Index: 120 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 5.7289. Min Range: -5.7289

Max Act: 5.6664. Min Act: -0.1700

Data Index: 194165 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 5.7289. Min Range: -5.7289

Max Act: 5.6977. Min Act: -0.1700

Data Index: 818909 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 5.7289. Min Range: -5.7289

Max Act: 5.6039. Min Act: -0.1700

Data Index: 373676 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 5.7289. Min Range: -5.7289

Max Act: 5.6039. Min Act: -0.1700

Data Index: 1254577 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 5.7289. Min Range: -5.7289

Max Act: 5.5727. Min Act: -0.1700

Data Index: 617978 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 5.7289. Min Range: -5.7289

Max Act: 5.6039. Min Act: -0.1700

Data Index: 1164770 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 5.7289. Min Range: -5.7289

Max Act: 5.6352. Min Act: -0.1700

Data Index: 5367 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 5.7289. Min Range: -5.7289

Max Act: 5.6664. Min Act: -0.1700

Data Index: 468927 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 5.7289. Min Range: -5.7289

Max Act: 5.6039. Min Act: -0.1700

Data Index: 1284995 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 5.7289. Min Range: -5.7289

Max Act: 5.5414. Min Act: -0.1700

Data Index: 215787 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 5.7289. Min Range: -5.7289

Max Act: 5.5414. Min Act: -0.1700

Data Index: 714961 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 5.7289. Min Range: -5.7289

Max Act: 5.5414. Min Act: -0.1700

Data Index: 633432 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 5.7289. Min Range: -5.7289

Max Act: 5.5414. Min Act: -0.1700

Data Index: 1213722 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 5.7289. Min Range: -5.7289

Max Act: 5.5727. Min Act: -0.1700

Data Index: 581710 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 5.7289. Min Range: -5.7289

Max Act: 5.5727. Min Act: -0.1700

Data Index: 1114627 (C4 (Web Text))

Max Activating Token Index: 322