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

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

Neuron 633 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: 3.5046. Min Range: -3.5046

Max Act: 3.5046. Min Act: -0.1700

Data Index: 48193 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 3.5046. Min Range: -3.5046

Max Act: 3.3948. Min Act: -0.1700

Data Index: 1593407 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 3.5046. Min Range: -3.5046

Max Act: 3.3948. Min Act: -0.1700

Data Index: 713574 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 3.5046. Min Range: -3.5046

Max Act: 3.3164. Min Act: -0.1700

Data Index: 1357269 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 3.5046. Min Range: -3.5046

Max Act: 3.2692. Min Act: -0.1700

Data Index: 1308562 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 3.5046. Min Range: -3.5046

Max Act: 3.2849. Min Act: -0.1700

Data Index: 1283630 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 3.5046. Min Range: -3.5046

Max Act: 3.2692. Min Act: -0.1700

Data Index: 277828 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 3.5046. Min Range: -3.5046

Max Act: 3.2692. Min Act: -0.1700

Data Index: 107374 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 3.5046. Min Range: -3.5046

Max Act: 3.2064. Min Act: -0.1700

Data Index: 454979 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 3.5046. Min Range: -3.5046

Max Act: 3.2378. Min Act: -0.1700

Data Index: 1372094 (Python Code)

Max Activating Token Index: 862

Text #10

Max Range: 3.5046. Min Range: -3.5046

Max Act: 3.2378. Min Act: -0.1700

Data Index: 725877 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 3.5046. Min Range: -3.5046

Max Act: 3.2378. Min Act: -0.1700

Data Index: 954871 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 3.5046. Min Range: -3.5046

Max Act: 3.2064. Min Act: -0.1700

Data Index: 1121561 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 3.5046. Min Range: -3.5046

Max Act: 3.2378. Min Act: -0.1700

Data Index: 1322228 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 3.5046. Min Range: -3.5046

Max Act: 3.2221. Min Act: -0.1700

Data Index: 1124654 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 3.5046. Min Range: -3.5046

Max Act: 3.2064. Min Act: -0.1700

Data Index: 208555 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 3.5046. Min Range: -3.5046

Max Act: 3.1749. Min Act: -0.1700

Data Index: 437207 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 3.5046. Min Range: -3.5046

Max Act: 3.2378. Min Act: -0.1700

Data Index: 598091 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 3.5046. Min Range: -3.5046

Max Act: 3.2064. Min Act: -0.1700

Data Index: 249192 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 3.5046. Min Range: -3.5046

Max Act: 3.1591. Min Act: -0.1700

Data Index: 1182150 (C4 (Web Text))

Max Activating Token Index: 456