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

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

Neuron 178 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.4732. Min Act: -0.1691

Data Index: 757587 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3948. Min Act: -0.1700

Data Index: 1349152 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3792. Min Act: -0.1700

Data Index: 1164305 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3635. Min Act: -0.1699

Data Index: 859493 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3635. Min Act: -0.1700

Data Index: 423334 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3478. Min Act: -0.1700

Data Index: 20827 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3792. Min Act: -0.1700

Data Index: 745026 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3792. Min Act: -0.1700

Data Index: 1164660 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3635. Min Act: -0.1700

Data Index: 710661 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3164. Min Act: -0.1700

Data Index: 1357283 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3792. Min Act: -0.1700

Data Index: 903465 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3478. Min Act: -0.1700

Data Index: 1293931 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3321. Min Act: -0.1700

Data Index: 1098054 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3164. Min Act: -0.1700

Data Index: 597334 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.2850. Min Act: -0.1700

Data Index: 640287 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3164. Min Act: -0.1700

Data Index: 1243288 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3321. Min Act: -0.1700

Data Index: 1099751 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.2378. Min Act: -0.1699

Data Index: 1248495 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.2850. Min Act: -0.1700

Data Index: 528531 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3164. Min Act: -0.1700

Data Index: 863824 (C4 (Web Text))

Max Activating Token Index: 421