Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1772 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.8707. Min Act: -0.1700

Data Index: 708374 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.7456. Min Act: -0.1700

Data Index: 562020 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.7143. Min Act: -0.1700

Data Index: 140985 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.6830. Min Act: -0.1700

Data Index: 1253778 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.6517. Min Act: -0.1700

Data Index: 323954 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.6830. Min Act: -0.1700

Data Index: 267742 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.6517. Min Act: -0.1700

Data Index: 855978 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.6830. Min Act: -0.1700

Data Index: 112532 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.6204. Min Act: -0.1700

Data Index: 560911 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.6204. Min Act: -0.1700

Data Index: 1120633 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.6204. Min Act: -0.1700

Data Index: 1093682 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.6204. Min Act: -0.1699

Data Index: 449027 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.5890. Min Act: -0.1700

Data Index: 807817 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.5577. Min Act: -0.1700

Data Index: 516396 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.6204. Min Act: -0.1700

Data Index: 1296585 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.6204. Min Act: -0.1700

Data Index: 793527 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.5890. Min Act: -0.1700

Data Index: 814916 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.5577. Min Act: -0.1700

Data Index: 1098686 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.5577. Min Act: -0.1700

Data Index: 820422 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.5577. Min Act: -0.1700

Data Index: 825680 (C4 (Web Text))

Max Activating Token Index: 271