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

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

Neuron 1904 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: 3.4564. Min Range: -3.4564

Max Act: 3.4564. Min Act: -0.1700

Data Index: 1468113 (Python Code)

Max Activating Token Index: 516

Text #1

Max Range: 3.4564. Min Range: -3.4564

Max Act: 3.3917. Min Act: -0.1153

Data Index: 726445 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 3.4564. Min Range: -3.4564

Max Act: 3.3238. Min Act: -0.1671

Data Index: 1010061 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 3.4564. Min Range: -3.4564

Max Act: 3.2518. Min Act: -0.1275

Data Index: 601053 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 3.4564. Min Range: -3.4564

Max Act: 3.2612. Min Act: -0.1153

Data Index: 1175415 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 3.4564. Min Range: -3.4564

Max Act: 3.2394. Min Act: -0.0854

Data Index: 506708 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 3.4564. Min Range: -3.4564

Max Act: 3.2348. Min Act: -0.1700

Data Index: 647356 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 3.4564. Min Range: -3.4564

Max Act: 3.2313. Min Act: -0.1649

Data Index: 724921 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 3.4564. Min Range: -3.4564

Max Act: 3.1868. Min Act: -0.0854

Data Index: 755483 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 3.4564. Min Range: -3.4564

Max Act: 3.1700. Min Act: -0.1450

Data Index: 1189526 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 3.4564. Min Range: -3.4564

Max Act: 3.1751. Min Act: -0.1688

Data Index: 673353 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 3.4564. Min Range: -3.4564

Max Act: 3.1578. Min Act: -0.1557

Data Index: 1588023 (Python Code)

Max Activating Token Index: 846

Text #12

Max Range: 3.4564. Min Range: -3.4564

Max Act: 3.1468. Min Act: -0.1660

Data Index: 1029593 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 3.4564. Min Range: -3.4564

Max Act: 3.1545. Min Act: -0.1672

Data Index: 929396 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 3.4564. Min Range: -3.4564

Max Act: 3.1316. Min Act: -0.1699

Data Index: 1019591 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 3.4564. Min Range: -3.4564

Max Act: 3.1226. Min Act: -0.0854

Data Index: 683085 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 3.4564. Min Range: -3.4564

Max Act: 3.1091. Min Act: -0.1510

Data Index: 66726 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 3.4564. Min Range: -3.4564

Max Act: 3.1032. Min Act: -0.1700

Data Index: 1155432 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 3.4564. Min Range: -3.4564

Max Act: 3.1054. Min Act: -0.1698

Data Index: 752978 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 3.4564. Min Range: -3.4564

Max Act: 3.1070. Min Act: -0.0854

Data Index: 294538 (C4 (Web Text))

Max Activating Token Index: 677