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

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

Neuron 335 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 7.3275. Min Range: -7.3275

Max Act: 7.3275. Min Act: -0.1700

Data Index: 613917 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 7.3275. Min Range: -7.3275

Max Act: 7.0775. Min Act: -0.1700

Data Index: 1228471 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 7.3275. Min Range: -7.3275

Max Act: 7.0150. Min Act: -0.1700

Data Index: 1131490 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 7.3275. Min Range: -7.3275

Max Act: 7.0150. Min Act: -0.1700

Data Index: 1152695 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 7.3275. Min Range: -7.3275

Max Act: 6.9213. Min Act: -0.1700

Data Index: 680232 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 7.3275. Min Range: -7.3275

Max Act: 6.9525. Min Act: -0.1700

Data Index: 592279 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 7.3275. Min Range: -7.3275

Max Act: 6.8900. Min Act: -0.1700

Data Index: 1016886 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 7.3275. Min Range: -7.3275

Max Act: 6.8588. Min Act: -0.1700

Data Index: 1173653 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 7.3275. Min Range: -7.3275

Max Act: 6.8900. Min Act: -0.1700

Data Index: 240666 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 7.3275. Min Range: -7.3275

Max Act: 6.8900. Min Act: -0.1700

Data Index: 728507 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 7.3275. Min Range: -7.3275

Max Act: 6.8275. Min Act: -0.1700

Data Index: 832589 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 7.3275. Min Range: -7.3275

Max Act: 6.7338. Min Act: -0.1700

Data Index: 629161 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 7.3275. Min Range: -7.3275

Max Act: 6.7963. Min Act: -0.1700

Data Index: 567401 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 7.3275. Min Range: -7.3275

Max Act: 6.7025. Min Act: -0.1700

Data Index: 337412 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 7.3275. Min Range: -7.3275

Max Act: 6.7025. Min Act: -0.1700

Data Index: 1159360 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 7.3275. Min Range: -7.3275

Max Act: 6.7338. Min Act: -0.1698

Data Index: 1357720 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 7.3275. Min Range: -7.3275

Max Act: 6.6088. Min Act: -0.1700

Data Index: 684010 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 7.3275. Min Range: -7.3275

Max Act: 6.7025. Min Act: -0.1700

Data Index: 1242157 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 7.3275. Min Range: -7.3275

Max Act: 6.6400. Min Act: -0.1700

Data Index: 345297 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 7.3275. Min Range: -7.3275

Max Act: 6.6400. Min Act: -0.1700

Data Index: 941147 (C4 (Web Text))

Max Activating Token Index: 353