Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 245 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.1290. Min Range: -5.1290

Max Act: 5.1290. Min Act: -0.1700

Data Index: 259236 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 5.1290. Min Range: -5.1290

Max Act: 5.0977. Min Act: -0.1700

Data Index: 1314011 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.9727. Min Act: -0.1700

Data Index: 672506 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.8790. Min Act: -0.1700

Data Index: 1095984 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.8790. Min Act: -0.1700

Data Index: 832433 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.7852. Min Act: -0.1700

Data Index: 604363 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.7852. Min Act: -0.1700

Data Index: 419055 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.7540. Min Act: -0.1700

Data Index: 532656 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.7852. Min Act: -0.1700

Data Index: 1200701 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.7227. Min Act: -0.1700

Data Index: 296143 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.8165. Min Act: -0.1700

Data Index: 905601 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.7852. Min Act: -0.1700

Data Index: 108897 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.7540. Min Act: -0.1700

Data Index: 1596283 (Python Code)

Max Activating Token Index: 770

Text #13

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.7540. Min Act: -0.1700

Data Index: 324983 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.7540. Min Act: -0.1700

Data Index: 757291 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.7227. Min Act: -0.1700

Data Index: 289616 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.7227. Min Act: -0.1700

Data Index: 20490 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.7540. Min Act: -0.1700

Data Index: 597514 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.7227. Min Act: -0.1700

Data Index: 610382 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.7227. Min Act: -0.1700

Data Index: 234768 (C4 (Web Text))

Max Activating Token Index: 70