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

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

Neuron 1482 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: 5.2321. Min Range: -5.2321

Max Act: 5.2321. Min Act: -0.1700

Data Index: 699954 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 5.2321. Min Range: -5.2321

Max Act: 5.1696. Min Act: -0.1700

Data Index: 745506 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 5.2321. Min Range: -5.2321

Max Act: 5.0759. Min Act: -0.1700

Data Index: 102429 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 5.2321. Min Range: -5.2321

Max Act: 5.1384. Min Act: -0.1700

Data Index: 1058018 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 5.2321. Min Range: -5.2321

Max Act: 5.0446. Min Act: -0.1700

Data Index: 454551 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 5.2321. Min Range: -5.2321

Max Act: 5.1071. Min Act: -0.1700

Data Index: 1164228 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 5.2321. Min Range: -5.2321

Max Act: 5.0446. Min Act: -0.1700

Data Index: 972676 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 5.2321. Min Range: -5.2321

Max Act: 5.0134. Min Act: -0.1700

Data Index: 1302549 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 5.2321. Min Range: -5.2321

Max Act: 5.0759. Min Act: -0.1700

Data Index: 1274593 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 5.2321. Min Range: -5.2321

Max Act: 5.0446. Min Act: -0.1700

Data Index: 630925 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 5.2321. Min Range: -5.2321

Max Act: 5.0446. Min Act: -0.1700

Data Index: 658347 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 5.2321. Min Range: -5.2321

Max Act: 5.0446. Min Act: -0.1700

Data Index: 563086 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 5.2321. Min Range: -5.2321

Max Act: 4.9821. Min Act: -0.1700

Data Index: 417803 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 5.2321. Min Range: -5.2321

Max Act: 5.0134. Min Act: -0.1700

Data Index: 399338 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 5.2321. Min Range: -5.2321

Max Act: 5.0134. Min Act: -0.1700

Data Index: 1150239 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 5.2321. Min Range: -5.2321

Max Act: 4.9509. Min Act: -0.1700

Data Index: 36317 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 5.2321. Min Range: -5.2321

Max Act: 4.9509. Min Act: -0.1700

Data Index: 972694 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 5.2321. Min Range: -5.2321

Max Act: 4.9509. Min Act: -0.1700

Data Index: 464413 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 5.2321. Min Range: -5.2321

Max Act: 4.9196. Min Act: -0.1700

Data Index: 1281687 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 5.2321. Min Range: -5.2321

Max Act: 4.9509. Min Act: -0.1700

Data Index: 1081182 (C4 (Web Text))

Max Activating Token Index: 552