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

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

Neuron 1399 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: 3.5858. Min Range: -3.5858

Max Act: 3.5858. Min Act: -0.1700

Data Index: 1235379 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.5232. Min Act: -0.1700

Data Index: 611527 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.3507. Min Act: -0.1700

Data Index: 687489 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.3193. Min Act: -0.1700

Data Index: 952557 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.3350. Min Act: -0.1700

Data Index: 590917 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.3036. Min Act: -0.1700

Data Index: 22924 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.3036. Min Act: -0.1700

Data Index: 1400751 (Python Code)

Max Activating Token Index: 937

Text #7

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.2879. Min Act: -0.1700

Data Index: 309077 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.2564. Min Act: -0.1700

Data Index: 363089 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.2564. Min Act: -0.1700

Data Index: 1138695 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.1935. Min Act: -0.1700

Data Index: 1059843 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.2250. Min Act: -0.1700

Data Index: 221514 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.1935. Min Act: -0.1700

Data Index: 1259733 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.1778. Min Act: -0.1700

Data Index: 367981 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.1778. Min Act: -0.1700

Data Index: 1536512 (Python Code)

Max Activating Token Index: 785

Text #15

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.1463. Min Act: -0.1700

Data Index: 1512281 (Python Code)

Max Activating Token Index: 814

Text #16

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.2093. Min Act: -0.1700

Data Index: 130066 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.1463. Min Act: -0.1700

Data Index: 687612 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.1463. Min Act: -0.1700

Data Index: 65699 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.0990. Min Act: -0.1700

Data Index: 973187 (C4 (Web Text))

Max Activating Token Index: 765