Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 432 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 5.7226. Min Range: -5.7226

Max Act: 5.7226. Min Act: -0.1700

Data Index: 559812 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 5.7226. Min Range: -5.7226

Max Act: 5.6497. Min Act: -0.1700

Data Index: 1175240 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 5.7226. Min Range: -5.7226

Max Act: 5.7092. Min Act: -0.1700

Data Index: 690361 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 5.7226. Min Range: -5.7226

Max Act: 5.5519. Min Act: -0.1700

Data Index: 721930 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 5.7226. Min Range: -5.7226

Max Act: 5.5086. Min Act: -0.1700

Data Index: 1027796 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 5.7226. Min Range: -5.7226

Max Act: 5.4638. Min Act: -0.1700

Data Index: 1314583 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 5.7226. Min Range: -5.7226

Max Act: 5.4073. Min Act: -0.1700

Data Index: 432324 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 5.7226. Min Range: -5.7226

Max Act: 5.4295. Min Act: -0.1700

Data Index: 322411 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 5.7226. Min Range: -5.7226

Max Act: 5.3969. Min Act: -0.1700

Data Index: 1343212 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 5.7226. Min Range: -5.7226

Max Act: 5.4219. Min Act: -0.1700

Data Index: 347338 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 5.7226. Min Range: -5.7226

Max Act: 5.4178. Min Act: -0.1700

Data Index: 140561 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 5.7226. Min Range: -5.7226

Max Act: 5.3935. Min Act: -0.1700

Data Index: 1316981 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 5.7226. Min Range: -5.7226

Max Act: 5.4139. Min Act: -0.1700

Data Index: 735332 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 5.7226. Min Range: -5.7226

Max Act: 5.4124. Min Act: -0.1700

Data Index: 432819 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 5.7226. Min Range: -5.7226

Max Act: 5.4279. Min Act: -0.1700

Data Index: 1037713 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 5.7226. Min Range: -5.7226

Max Act: 5.4404. Min Act: -0.1700

Data Index: 615027 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 5.7226. Min Range: -5.7226

Max Act: 5.4847. Min Act: -0.1700

Data Index: 871795 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 5.7226. Min Range: -5.7226

Max Act: 5.3358. Min Act: -0.1700

Data Index: 663688 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 5.7226. Min Range: -5.7226

Max Act: 5.4000. Min Act: -0.1700

Data Index: 244173 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 5.7226. Min Range: -5.7226

Max Act: 5.4088. Min Act: -0.1700

Data Index: 453950 (C4 (Web Text))

Max Activating Token Index: 400