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

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

Neuron 1811 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: 3.9279. Min Range: -3.9279

Max Act: 3.8028. Min Act: -0.1700

Data Index: 199267 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 3.9279. Min Range: -3.9279

Max Act: 3.9279. Min Act: -0.1700

Data Index: 276289 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 3.9279. Min Range: -3.9279

Max Act: 3.7402. Min Act: -0.1700

Data Index: 656711 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 3.9279. Min Range: -3.9279

Max Act: 3.7715. Min Act: -0.1700

Data Index: 322171 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 3.9279. Min Range: -3.9279

Max Act: 3.7715. Min Act: -0.1700

Data Index: 991179 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 3.9279. Min Range: -3.9279

Max Act: 3.7089. Min Act: -0.1700

Data Index: 863048 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 3.9279. Min Range: -3.9279

Max Act: 3.7715. Min Act: -0.1700

Data Index: 898093 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 3.9279. Min Range: -3.9279

Max Act: 3.7402. Min Act: -0.1700

Data Index: 61965 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.9279. Min Range: -3.9279

Max Act: 3.6150. Min Act: -0.1700

Data Index: 111328 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 3.9279. Min Range: -3.9279

Max Act: 3.7089. Min Act: -0.1700

Data Index: 947202 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 3.9279. Min Range: -3.9279

Max Act: 3.6463. Min Act: -0.1700

Data Index: 634107 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 3.9279. Min Range: -3.9279

Max Act: 3.6150. Min Act: -0.1700

Data Index: 1057968 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 3.9279. Min Range: -3.9279

Max Act: 3.5837. Min Act: -0.1700

Data Index: 52219 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 3.9279. Min Range: -3.9279

Max Act: 3.5211. Min Act: -0.1700

Data Index: 1246369 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 3.9279. Min Range: -3.9279

Max Act: 3.5524. Min Act: -0.1700

Data Index: 5439 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 3.9279. Min Range: -3.9279

Max Act: 3.5837. Min Act: -0.1700

Data Index: 383938 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 3.9279. Min Range: -3.9279

Max Act: 3.6463. Min Act: -0.1700

Data Index: 364819 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 3.9279. Min Range: -3.9279

Max Act: 3.4897. Min Act: -0.1700

Data Index: 1056112 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 3.9279. Min Range: -3.9279

Max Act: 3.5524. Min Act: -0.1700

Data Index: 157746 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 3.9279. Min Range: -3.9279

Max Act: 3.5211. Min Act: -0.1700

Data Index: 124024 (C4 (Web Text))

Max Activating Token Index: 112