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

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

Neuron 270 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0871. Min Range: -3.0871

Max Act: 3.0871. Min Act: -0.1700

Data Index: 498359 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.8973. Min Act: -0.1700

Data Index: 814140 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.8656. Min Act: -0.1700

Data Index: 1110722 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.8179. Min Act: -0.1700

Data Index: 1111171 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.8338. Min Act: -0.1700

Data Index: 1462 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.8338. Min Act: -0.1700

Data Index: 220137 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.8179. Min Act: -0.1700

Data Index: 554176 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.8179. Min Act: -0.1700

Data Index: 587152 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.8179. Min Act: -0.1700

Data Index: 89015 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.8020. Min Act: -0.1700

Data Index: 233449 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.8179. Min Act: -0.1700

Data Index: 802291 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.7860. Min Act: -0.1700

Data Index: 580536 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.7701. Min Act: -0.1700

Data Index: 1204553 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.7701. Min Act: -0.1700

Data Index: 562127 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.7541. Min Act: -0.1700

Data Index: 1272432 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.7541. Min Act: -0.1700

Data Index: 1004953 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.7382. Min Act: -0.1700

Data Index: 890551 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.7222. Min Act: -0.1700

Data Index: 1326279 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.7062. Min Act: -0.1700

Data Index: 875077 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.7382. Min Act: -0.1700

Data Index: 443971 (C4 (Web Text))

Max Activating Token Index: 123