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

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

Neuron 534 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.7866. Min Act: -0.1700

Data Index: 83131 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.7553. Min Act: -0.1700

Data Index: 1139027 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.7553. Min Act: -0.1700

Data Index: 506789 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.7553. Min Act: -0.1700

Data Index: 375598 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.7553. Min Act: -0.1700

Data Index: 971773 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.7240. Min Act: -0.1700

Data Index: 1091228 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.6927. Min Act: -0.1700

Data Index: 262984 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.6927. Min Act: -0.1700

Data Index: 751705 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.6614. Min Act: -0.1700

Data Index: 732795 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.6927. Min Act: -0.1700

Data Index: 196532 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.6927. Min Act: -0.1700

Data Index: 725286 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.6614. Min Act: -0.1700

Data Index: 1098139 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.6614. Min Act: -0.1700

Data Index: 1114508 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.6614. Min Act: -0.1700

Data Index: 921533 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.6614. Min Act: -0.1700

Data Index: 1333880 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.6301. Min Act: -0.1700

Data Index: 403331 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.6927. Min Act: -0.1700

Data Index: 489245 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.6614. Min Act: -0.1700

Data Index: 170992 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.6301. Min Act: -0.1700

Data Index: 168725 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.6301. Min Act: -0.1700

Data Index: 205084 (C4 (Web Text))

Max Activating Token Index: 9