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

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

Neuron 264 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: 3.5360. Min Range: -3.5360

Max Act: 3.5360. Min Act: -0.1700

Data Index: 458301 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 3.5360. Min Range: -3.5360

Max Act: 3.4886. Min Act: -0.1700

Data Index: 1081030 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 3.5360. Min Range: -3.5360

Max Act: 3.4863. Min Act: -0.1700

Data Index: 7246 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 3.5360. Min Range: -3.5360

Max Act: 3.4623. Min Act: -0.1699

Data Index: 926309 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 3.5360. Min Range: -3.5360

Max Act: 3.4458. Min Act: -0.1700

Data Index: 1217108 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 3.5360. Min Range: -3.5360

Max Act: 3.4478. Min Act: -0.1700

Data Index: 53339 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 3.5360. Min Range: -3.5360

Max Act: 3.4216. Min Act: -0.1700

Data Index: 112965 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 3.5360. Min Range: -3.5360

Max Act: 3.3848. Min Act: -0.1700

Data Index: 549144 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 3.5360. Min Range: -3.5360

Max Act: 3.4152. Min Act: -0.1700

Data Index: 859455 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 3.5360. Min Range: -3.5360

Max Act: 3.4193. Min Act: -0.1700

Data Index: 457458 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 3.5360. Min Range: -3.5360

Max Act: 3.4104. Min Act: -0.1700

Data Index: 1355373 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 3.5360. Min Range: -3.5360

Max Act: 3.3459. Min Act: -0.1700

Data Index: 696565 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 3.5360. Min Range: -3.5360

Max Act: 3.3881. Min Act: -0.1699

Data Index: 550576 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 3.5360. Min Range: -3.5360

Max Act: 3.3767. Min Act: -0.1700

Data Index: 42230 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 3.5360. Min Range: -3.5360

Max Act: 3.3523. Min Act: -0.1700

Data Index: 892626 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 3.5360. Min Range: -3.5360

Max Act: 3.3621. Min Act: -0.1700

Data Index: 48069 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 3.5360. Min Range: -3.5360

Max Act: 3.3717. Min Act: -0.1700

Data Index: 348644 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 3.5360. Min Range: -3.5360

Max Act: 3.3724. Min Act: -0.1700

Data Index: 1065739 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 3.5360. Min Range: -3.5360

Max Act: 3.3688. Min Act: -0.1700

Data Index: 853664 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 3.5360. Min Range: -3.5360

Max Act: 3.3498. Min Act: -0.1700

Data Index: 765967 (C4 (Web Text))

Max Activating Token Index: 467