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

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

Neuron 1312 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: 5.7347. Min Range: -5.7347

Max Act: 5.7347. Min Act: -0.1700

Data Index: 894416 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 5.7347. Min Range: -5.7347

Max Act: 5.6409. Min Act: -0.1700

Data Index: 1103869 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 5.7347. Min Range: -5.7347

Max Act: 5.5472. Min Act: -0.1700

Data Index: 673368 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 5.7347. Min Range: -5.7347

Max Act: 5.4222. Min Act: -0.1700

Data Index: 524197 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 5.7347. Min Range: -5.7347

Max Act: 5.4534. Min Act: -0.1700

Data Index: 1024010 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 5.7347. Min Range: -5.7347

Max Act: 5.3909. Min Act: -0.1700

Data Index: 794443 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 5.7347. Min Range: -5.7347

Max Act: 5.3597. Min Act: -0.1700

Data Index: 131222 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 5.7347. Min Range: -5.7347

Max Act: 5.3909. Min Act: -0.1700

Data Index: 37989 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 5.7347. Min Range: -5.7347

Max Act: 5.3909. Min Act: -0.1700

Data Index: 416895 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 5.7347. Min Range: -5.7347

Max Act: 5.3284. Min Act: -0.1700

Data Index: 267671 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 5.7347. Min Range: -5.7347

Max Act: 5.2972. Min Act: -0.1700

Data Index: 397834 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 5.7347. Min Range: -5.7347

Max Act: 5.2972. Min Act: -0.1700

Data Index: 558333 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 5.7347. Min Range: -5.7347

Max Act: 5.2659. Min Act: -0.1700

Data Index: 1095701 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 5.7347. Min Range: -5.7347

Max Act: 5.2972. Min Act: -0.1700

Data Index: 236740 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 5.7347. Min Range: -5.7347

Max Act: 5.2659. Min Act: -0.1700

Data Index: 905010 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 5.7347. Min Range: -5.7347

Max Act: 5.2659. Min Act: -0.1700

Data Index: 33326 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 5.7347. Min Range: -5.7347

Max Act: 5.2659. Min Act: -0.1700

Data Index: 478209 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 5.7347. Min Range: -5.7347

Max Act: 5.2347. Min Act: -0.1700

Data Index: 150426 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 5.7347. Min Range: -5.7347

Max Act: 5.2659. Min Act: -0.1700

Data Index: 188243 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 5.7347. Min Range: -5.7347

Max Act: 5.2659. Min Act: -0.1700

Data Index: 783036 (C4 (Web Text))

Max Activating Token Index: 121