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

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

Neuron 231 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.2324. Min Range: -3.2324

Max Act: 3.2324. Min Act: -0.1700

Data Index: 918045 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 3.2324. Min Range: -3.2324

Max Act: 3.2324. Min Act: -0.1700

Data Index: 255768 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 3.2324. Min Range: -3.2324

Max Act: 3.1694. Min Act: -0.1700

Data Index: 361507 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 3.2324. Min Range: -3.2324

Max Act: 3.1694. Min Act: -0.1700

Data Index: 221538 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 3.2324. Min Range: -3.2324

Max Act: 3.1379. Min Act: -0.1699

Data Index: 969209 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 3.2324. Min Range: -3.2324

Max Act: 3.1379. Min Act: -0.1700

Data Index: 594753 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 3.2324. Min Range: -3.2324

Max Act: 3.1064. Min Act: -0.1700

Data Index: 1034326 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 3.2324. Min Range: -3.2324

Max Act: 3.1064. Min Act: -0.1700

Data Index: 1034998 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 3.2324. Min Range: -3.2324

Max Act: 3.0749. Min Act: -0.1700

Data Index: 1026062 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 3.2324. Min Range: -3.2324

Max Act: 3.0749. Min Act: -0.1700

Data Index: 926705 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 3.2324. Min Range: -3.2324

Max Act: 3.1064. Min Act: -0.1700

Data Index: 406596 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 3.2324. Min Range: -3.2324

Max Act: 3.1064. Min Act: -0.1700

Data Index: 615286 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 3.2324. Min Range: -3.2324

Max Act: 3.0749. Min Act: -0.1700

Data Index: 247816 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 3.2324. Min Range: -3.2324

Max Act: 3.0749. Min Act: -0.1700

Data Index: 299223 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 3.2324. Min Range: -3.2324

Max Act: 3.0433. Min Act: -0.1700

Data Index: 25244 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 3.2324. Min Range: -3.2324

Max Act: 3.0433. Min Act: -0.1700

Data Index: 1224215 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 3.2324. Min Range: -3.2324

Max Act: 3.0433. Min Act: -0.1700

Data Index: 787365 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 3.2324. Min Range: -3.2324

Max Act: 3.0433. Min Act: -0.1700

Data Index: 922069 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 3.2324. Min Range: -3.2324

Max Act: 3.0433. Min Act: -0.1700

Data Index: 461122 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 3.2324. Min Range: -3.2324

Max Act: 3.0117. Min Act: -0.1700

Data Index: 824082 (C4 (Web Text))

Max Activating Token Index: 573