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

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

Neuron 507 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: 5.4204. Min Range: -5.4204

Max Act: 5.4204. Min Act: -0.1700

Data Index: 541237 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 5.4204. Min Range: -5.4204

Max Act: 5.1704. Min Act: -0.1700

Data Index: 729238 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 5.4204. Min Range: -5.4204

Max Act: 5.1704. Min Act: -0.1700

Data Index: 857349 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 5.4204. Min Range: -5.4204

Max Act: 5.1704. Min Act: -0.1700

Data Index: 382195 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 5.4204. Min Range: -5.4204

Max Act: 4.8891. Min Act: -0.1700

Data Index: 928213 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 5.4204. Min Range: -5.4204

Max Act: 5.0141. Min Act: -0.1700

Data Index: 624628 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 5.4204. Min Range: -5.4204

Max Act: 4.9829. Min Act: -0.1700

Data Index: 657026 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 5.4204. Min Range: -5.4204

Max Act: 4.9204. Min Act: -0.1700

Data Index: 178255 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 5.4204. Min Range: -5.4204

Max Act: 5.0141. Min Act: -0.1700

Data Index: 688286 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 5.4204. Min Range: -5.4204

Max Act: 4.9204. Min Act: -0.1700

Data Index: 1106345 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 5.4204. Min Range: -5.4204

Max Act: 4.8891. Min Act: -0.1700

Data Index: 1161822 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 5.4204. Min Range: -5.4204

Max Act: 4.7954. Min Act: -0.1700

Data Index: 1166114 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 5.4204. Min Range: -5.4204

Max Act: 4.8891. Min Act: -0.1700

Data Index: 109967 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 5.4204. Min Range: -5.4204

Max Act: 4.8266. Min Act: -0.1700

Data Index: 1171635 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 5.4204. Min Range: -5.4204

Max Act: 4.7641. Min Act: -0.1700

Data Index: 73491 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 5.4204. Min Range: -5.4204

Max Act: 4.8579. Min Act: -0.1700

Data Index: 1210424 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 5.4204. Min Range: -5.4204

Max Act: 4.8266. Min Act: -0.1700

Data Index: 417960 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 5.4204. Min Range: -5.4204

Max Act: 4.8266. Min Act: -0.1700

Data Index: 478547 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 5.4204. Min Range: -5.4204

Max Act: 4.7329. Min Act: -0.1700

Data Index: 628203 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 5.4204. Min Range: -5.4204

Max Act: 4.7329. Min Act: -0.1700

Data Index: 777924 (C4 (Web Text))

Max Activating Token Index: 416