Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 198 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.7379. Min Range: -3.7379

Max Act: 3.7379. Min Act: -0.1700

Data Index: 962309 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 3.7379. Min Range: -3.7379

Max Act: 3.6127. Min Act: -0.1700

Data Index: 1074269 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 3.7379. Min Range: -3.7379

Max Act: 3.5031. Min Act: -0.1700

Data Index: 382096 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 3.7379. Min Range: -3.7379

Max Act: 3.4717. Min Act: -0.1700

Data Index: 1315680 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 3.7379. Min Range: -3.7379

Max Act: 3.3933. Min Act: -0.1700

Data Index: 1268213 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 3.7379. Min Range: -3.7379

Max Act: 3.4247. Min Act: -0.1700

Data Index: 1271979 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 3.7379. Min Range: -3.7379

Max Act: 3.3776. Min Act: -0.1700

Data Index: 361743 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 3.7379. Min Range: -3.7379

Max Act: 3.3776. Min Act: -0.1700

Data Index: 892464 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 3.7379. Min Range: -3.7379

Max Act: 3.3463. Min Act: -0.1700

Data Index: 193010 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 3.7379. Min Range: -3.7379

Max Act: 3.2834. Min Act: -0.1700

Data Index: 97208 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 3.7379. Min Range: -3.7379

Max Act: 3.2677. Min Act: -0.1700

Data Index: 792275 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 3.7379. Min Range: -3.7379

Max Act: 3.2363. Min Act: -0.1700

Data Index: 334255 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 3.7379. Min Range: -3.7379

Max Act: 3.2363. Min Act: -0.1700

Data Index: 990836 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 3.7379. Min Range: -3.7379

Max Act: 3.2206. Min Act: -0.1700

Data Index: 490683 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 3.7379. Min Range: -3.7379

Max Act: 3.2206. Min Act: -0.1700

Data Index: 1237977 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 3.7379. Min Range: -3.7379

Max Act: 3.2048. Min Act: -0.1700

Data Index: 727769 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 3.7379. Min Range: -3.7379

Max Act: 3.2206. Min Act: -0.1700

Data Index: 463256 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 3.7379. Min Range: -3.7379

Max Act: 3.2363. Min Act: -0.1700

Data Index: 703905 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 3.7379. Min Range: -3.7379

Max Act: 3.2520. Min Act: -0.1700

Data Index: 1270228 (C4 (Web Text))

Max Activating Token Index: 652

Text #19

Max Range: 3.7379. Min Range: -3.7379

Max Act: 3.1891. Min Act: -0.1700

Data Index: 1007756 (C4 (Web Text))

Max Activating Token Index: 896