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

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

Neuron 1828 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: 5.8164. Min Range: -5.8164

Max Act: 5.8164. Min Act: -0.1700

Data Index: 710765 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 5.8164. Min Range: -5.8164

Max Act: 5.6601. Min Act: -0.1700

Data Index: 134139 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 5.8164. Min Range: -5.8164

Max Act: 5.4414. Min Act: -0.1700

Data Index: 1094428 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 5.8164. Min Range: -5.8164

Max Act: 5.4726. Min Act: -0.1700

Data Index: 832056 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 5.8164. Min Range: -5.8164

Max Act: 5.3789. Min Act: -0.1700

Data Index: 710782 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 5.8164. Min Range: -5.8164

Max Act: 5.3164. Min Act: -0.1700

Data Index: 864441 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 5.8164. Min Range: -5.8164

Max Act: 5.3476. Min Act: -0.1700

Data Index: 109439 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 5.8164. Min Range: -5.8164

Max Act: 5.1914. Min Act: -0.1700

Data Index: 159697 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 5.8164. Min Range: -5.8164

Max Act: 5.2226. Min Act: -0.1700

Data Index: 939567 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 5.8164. Min Range: -5.8164

Max Act: 5.2539. Min Act: -0.1700

Data Index: 1075053 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 5.8164. Min Range: -5.8164

Max Act: 5.1914. Min Act: -0.1700

Data Index: 871111 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 5.8164. Min Range: -5.8164

Max Act: 5.1601. Min Act: -0.1700

Data Index: 1092653 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 5.8164. Min Range: -5.8164

Max Act: 5.1914. Min Act: -0.1700

Data Index: 371623 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 5.8164. Min Range: -5.8164

Max Act: 5.1914. Min Act: -0.1700

Data Index: 110745 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 5.8164. Min Range: -5.8164

Max Act: 5.0976. Min Act: -0.1700

Data Index: 877784 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 5.8164. Min Range: -5.8164

Max Act: 5.1289. Min Act: -0.1700

Data Index: 338479 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 5.8164. Min Range: -5.8164

Max Act: 5.1289. Min Act: -0.1700

Data Index: 1081444 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 5.8164. Min Range: -5.8164

Max Act: 5.0976. Min Act: -0.1700

Data Index: 806716 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 5.8164. Min Range: -5.8164

Max Act: 5.1601. Min Act: -0.1700

Data Index: 586177 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 5.8164. Min Range: -5.8164

Max Act: 5.1289. Min Act: -0.1700

Data Index: 232431 (C4 (Web Text))

Max Activating Token Index: 858