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

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

Neuron 872 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: 5.3302. Min Range: -5.3302

Max Act: 5.3302. Min Act: -0.1700

Data Index: 1152881 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 5.3302. Min Range: -5.3302

Max Act: 5.2364. Min Act: -0.1700

Data Index: 1130199 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 5.3302. Min Range: -5.3302

Max Act: 5.0802. Min Act: -0.1700

Data Index: 1339045 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 5.3302. Min Range: -5.3302

Max Act: 5.1427. Min Act: -0.1700

Data Index: 473026 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 5.3302. Min Range: -5.3302

Max Act: 5.1114. Min Act: -0.1700

Data Index: 184026 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 5.3302. Min Range: -5.3302

Max Act: 5.1114. Min Act: -0.1700

Data Index: 454970 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 5.3302. Min Range: -5.3302

Max Act: 5.0489. Min Act: -0.1700

Data Index: 964604 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 5.3302. Min Range: -5.3302

Max Act: 5.0802. Min Act: -0.1700

Data Index: 1085247 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 5.3302. Min Range: -5.3302

Max Act: 5.0802. Min Act: -0.1700

Data Index: 602758 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 5.3302. Min Range: -5.3302

Max Act: 5.0489. Min Act: -0.1700

Data Index: 462992 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 5.3302. Min Range: -5.3302

Max Act: 5.1114. Min Act: -0.1700

Data Index: 1058746 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 5.3302. Min Range: -5.3302

Max Act: 5.0489. Min Act: -0.1700

Data Index: 1306887 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 5.3302. Min Range: -5.3302

Max Act: 5.0802. Min Act: -0.1700

Data Index: 272047 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 5.3302. Min Range: -5.3302

Max Act: 5.0802. Min Act: -0.1700

Data Index: 636558 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 5.3302. Min Range: -5.3302

Max Act: 4.9239. Min Act: -0.1700

Data Index: 1266590 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 5.3302. Min Range: -5.3302

Max Act: 4.9552. Min Act: -0.1700

Data Index: 113597 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 5.3302. Min Range: -5.3302

Max Act: 4.9864. Min Act: -0.1700

Data Index: 132963 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 5.3302. Min Range: -5.3302

Max Act: 5.0177. Min Act: -0.1700

Data Index: 513148 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 5.3302. Min Range: -5.3302

Max Act: 5.0177. Min Act: -0.1700

Data Index: 136215 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 5.3302. Min Range: -5.3302

Max Act: 4.9552. Min Act: -0.1700

Data Index: 818351 (C4 (Web Text))

Max Activating Token Index: 809