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

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

Neuron 928 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: 5.3711. Min Range: -5.3711

Max Act: 5.3711. Min Act: -0.1700

Data Index: 236152 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 5.3711. Min Range: -5.3711

Max Act: 5.2149. Min Act: -0.1700

Data Index: 1265127 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 5.3711. Min Range: -5.3711

Max Act: 5.1836. Min Act: -0.1700

Data Index: 234182 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 5.3711. Min Range: -5.3711

Max Act: 5.1836. Min Act: -0.1700

Data Index: 288652 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 5.3711. Min Range: -5.3711

Max Act: 5.1211. Min Act: -0.1700

Data Index: 968388 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 5.3711. Min Range: -5.3711

Max Act: 5.0899. Min Act: -0.1700

Data Index: 688884 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 5.3711. Min Range: -5.3711

Max Act: 5.0274. Min Act: -0.1700

Data Index: 370840 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 5.3711. Min Range: -5.3711

Max Act: 5.0586. Min Act: -0.1700

Data Index: 328028 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 5.3711. Min Range: -5.3711

Max Act: 5.0274. Min Act: -0.1700

Data Index: 160290 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 5.3711. Min Range: -5.3711

Max Act: 5.0274. Min Act: -0.1700

Data Index: 1344050 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 5.3711. Min Range: -5.3711

Max Act: 5.0274. Min Act: -0.1700

Data Index: 932204 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 5.3711. Min Range: -5.3711

Max Act: 5.0274. Min Act: -0.1700

Data Index: 999601 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 5.3711. Min Range: -5.3711

Max Act: 5.0274. Min Act: -0.1700

Data Index: 1006342 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 5.3711. Min Range: -5.3711

Max Act: 4.9961. Min Act: -0.1700

Data Index: 833750 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 5.3711. Min Range: -5.3711

Max Act: 4.9961. Min Act: -0.1700

Data Index: 2300 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 5.3711. Min Range: -5.3711

Max Act: 4.9649. Min Act: -0.1700

Data Index: 333326 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 5.3711. Min Range: -5.3711

Max Act: 4.9649. Min Act: -0.1700

Data Index: 1293466 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 5.3711. Min Range: -5.3711

Max Act: 4.9649. Min Act: -0.1700

Data Index: 889919 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 5.3711. Min Range: -5.3711

Max Act: 4.9336. Min Act: -0.1700

Data Index: 1335270 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 5.3711. Min Range: -5.3711

Max Act: 4.9336. Min Act: -0.1700

Data Index: 944025 (C4 (Web Text))

Max Activating Token Index: 314