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

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

Neuron 925 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.9916. Min Act: -0.1700

Data Index: 1349776 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.9290. Min Act: -0.1700

Data Index: 1010934 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.8665. Min Act: -0.1700

Data Index: 450629 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.8665. Min Act: -0.1700

Data Index: 638124 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.8352. Min Act: -0.1700

Data Index: 690263 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.8352. Min Act: -0.1700

Data Index: 1295363 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.8352. Min Act: -0.1700

Data Index: 318823 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.8352. Min Act: -0.1700

Data Index: 458793 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.8352. Min Act: -0.1700

Data Index: 487101 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.8039. Min Act: -0.1700

Data Index: 858967 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.7727. Min Act: -0.1700

Data Index: 801488 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.7727. Min Act: -0.1700

Data Index: 400541 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.7414. Min Act: -0.1700

Data Index: 33809 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.7414. Min Act: -0.1700

Data Index: 343734 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.6631. Min Act: -0.1700

Data Index: 1303383 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.6788. Min Act: -0.1700

Data Index: 907366 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.6788. Min Act: -0.1700

Data Index: 537413 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.7101. Min Act: -0.1700

Data Index: 1280453 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.6162. Min Act: -0.1700

Data Index: 745283 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.6318. Min Act: -0.1700

Data Index: 223260 (C4 (Web Text))

Max Activating Token Index: 609