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

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

Neuron 1071 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: 11.6885. Min Range: -11.6885

Max Act: 11.6885. Min Act: -0.1700

Data Index: 351424 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 11.6885. Min Range: -11.6885

Max Act: 11.3135. Min Act: -0.1700

Data Index: 490140 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 11.6885. Min Range: -11.6885

Max Act: 11.0010. Min Act: -0.1700

Data Index: 880202 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 11.6885. Min Range: -11.6885

Max Act: 10.7510. Min Act: -0.1700

Data Index: 1305859 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 11.6885. Min Range: -11.6885

Max Act: 10.6885. Min Act: -0.1700

Data Index: 645664 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 11.6885. Min Range: -11.6885

Max Act: 10.6885. Min Act: -0.1700

Data Index: 345745 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 11.6885. Min Range: -11.6885

Max Act: 10.6260. Min Act: -0.1700

Data Index: 479436 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 11.6885. Min Range: -11.6885

Max Act: 10.6885. Min Act: -0.1700

Data Index: 1135385 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 11.6885. Min Range: -11.6885

Max Act: 10.6260. Min Act: -0.1700

Data Index: 719581 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 11.6885. Min Range: -11.6885

Max Act: 10.8135. Min Act: -0.1700

Data Index: 1130398 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 11.6885. Min Range: -11.6885

Max Act: 10.5010. Min Act: -0.1700

Data Index: 682952 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 11.6885. Min Range: -11.6885

Max Act: 10.5010. Min Act: -0.1700

Data Index: 294647 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 11.6885. Min Range: -11.6885

Max Act: 10.5635. Min Act: -0.1700

Data Index: 1335959 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 11.6885. Min Range: -11.6885

Max Act: 10.4385. Min Act: -0.1700

Data Index: 909103 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 11.6885. Min Range: -11.6885

Max Act: 10.4385. Min Act: -0.1700

Data Index: 437999 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 11.6885. Min Range: -11.6885

Max Act: 10.4385. Min Act: -0.1700

Data Index: 860334 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 11.6885. Min Range: -11.6885

Max Act: 10.3135. Min Act: -0.1700

Data Index: 291842 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 11.6885. Min Range: -11.6885

Max Act: 10.2510. Min Act: -0.1700

Data Index: 64600 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 11.6885. Min Range: -11.6885

Max Act: 10.2510. Min Act: -0.1700

Data Index: 657583 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 11.6885. Min Range: -11.6885

Max Act: 10.2510. Min Act: -0.1700

Data Index: 660715 (C4 (Web Text))

Max Activating Token Index: 281