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

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

Neuron 1515 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8447. Min Range: -5.8447

Max Act: 5.6885. Min Act: -0.1700

Data Index: 183433 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 5.8447. Min Range: -5.8447

Max Act: 5.8447. Min Act: -0.1700

Data Index: 156329 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 5.8447. Min Range: -5.8447

Max Act: 5.0322. Min Act: -0.1700

Data Index: 323402 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 5.8447. Min Range: -5.8447

Max Act: 5.0947. Min Act: -0.1700

Data Index: 291140 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 5.8447. Min Range: -5.8447

Max Act: 5.0947. Min Act: -0.1699

Data Index: 79421 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 5.8447. Min Range: -5.8447

Max Act: 4.9385. Min Act: -0.1700

Data Index: 343150 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 5.8447. Min Range: -5.8447

Max Act: 4.9072. Min Act: -0.1700

Data Index: 458932 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 5.8447. Min Range: -5.8447

Max Act: 4.9072. Min Act: -0.1700

Data Index: 1036417 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 5.8447. Min Range: -5.8447

Max Act: 5.0635. Min Act: -0.1700

Data Index: 1357558 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 5.8447. Min Range: -5.8447

Max Act: 4.8760. Min Act: -0.1700

Data Index: 666966 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 5.8447. Min Range: -5.8447

Max Act: 4.6885. Min Act: -0.1700

Data Index: 966457 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 5.8447. Min Range: -5.8447

Max Act: 5.1260. Min Act: -0.1700

Data Index: 1154468 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 5.8447. Min Range: -5.8447

Max Act: 4.9385. Min Act: -0.1700

Data Index: 664258 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 5.8447. Min Range: -5.8447

Max Act: 5.0010. Min Act: -0.1700

Data Index: 1173405 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 5.8447. Min Range: -5.8447

Max Act: 4.9072. Min Act: -0.1700

Data Index: 665523 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 5.8447. Min Range: -5.8447

Max Act: 4.8760. Min Act: -0.1700

Data Index: 1194649 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 5.8447. Min Range: -5.8447

Max Act: 5.0947. Min Act: -0.1700

Data Index: 873048 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 5.8447. Min Range: -5.8447

Max Act: 4.8760. Min Act: -0.1700

Data Index: 287346 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 5.8447. Min Range: -5.8447

Max Act: 4.8760. Min Act: -0.1699

Data Index: 25381 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 5.8447. Min Range: -5.8447

Max Act: 4.7510. Min Act: -0.1700

Data Index: 1187235 (C4 (Web Text))

Max Activating Token Index: 428