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

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

Neuron 1866 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: 3.6897. Min Range: -3.6897

Max Act: 3.6897. Min Act: -0.1700

Data Index: 4836 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.5957. Min Act: -0.1700

Data Index: 801877 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.5644. Min Act: -0.1700

Data Index: 1142182 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.5331. Min Act: -0.1700

Data Index: 592183 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.4077. Min Act: -0.1700

Data Index: 1170411 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.5331. Min Act: -0.1700

Data Index: 239191 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.5331. Min Act: -0.1700

Data Index: 1300398 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.4704. Min Act: -0.1700

Data Index: 623988 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.4391. Min Act: -0.1700

Data Index: 692770 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.4077. Min Act: -0.1700

Data Index: 640335 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.3449. Min Act: -0.1700

Data Index: 1350606 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.3135. Min Act: -0.1700

Data Index: 1182029 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.3135. Min Act: -0.1700

Data Index: 1059329 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.3449. Min Act: -0.1700

Data Index: 507503 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.3449. Min Act: -0.1700

Data Index: 1314174 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.3449. Min Act: -0.1700

Data Index: 552795 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.3135. Min Act: -0.1700

Data Index: 877080 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.3763. Min Act: -0.1700

Data Index: 68378 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.3763. Min Act: -0.1700

Data Index: 1226080 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.2821. Min Act: -0.1700

Data Index: 885119 (C4 (Web Text))

Max Activating Token Index: 917