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

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

Neuron 51 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: 3.2523. Min Range: -3.2523

Max Act: 3.2523. Min Act: -0.1700

Data Index: 443308 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.1304. Min Act: -0.1700

Data Index: 61815 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.0919. Min Act: -0.1700

Data Index: 973925 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.0705. Min Act: -0.1700

Data Index: 995033 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.0730. Min Act: -0.1700

Data Index: 884388 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.0180. Min Act: -0.1700

Data Index: 628178 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.0402. Min Act: -0.1700

Data Index: 1238852 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.0199. Min Act: -0.1700

Data Index: 1458351 (Python Code)

Max Activating Token Index: 32

Text #8

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.0179. Min Act: -0.1700

Data Index: 622477 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.0172. Min Act: -0.1700

Data Index: 625334 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 3.2523. Min Range: -3.2523

Max Act: 2.9896. Min Act: -0.1700

Data Index: 274477 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 3.2523. Min Range: -3.2523

Max Act: 2.9846. Min Act: -0.1700

Data Index: 1468814 (Python Code)

Max Activating Token Index: 710

Text #12

Max Range: 3.2523. Min Range: -3.2523

Max Act: 2.9514. Min Act: -0.1700

Data Index: 644316 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 3.2523. Min Range: -3.2523

Max Act: 2.9518. Min Act: -0.1700

Data Index: 150427 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 3.2523. Min Range: -3.2523

Max Act: 2.9594. Min Act: -0.1700

Data Index: 849962 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 3.2523. Min Range: -3.2523

Max Act: 2.9701. Min Act: -0.1700

Data Index: 102278 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 3.2523. Min Range: -3.2523

Max Act: 2.9418. Min Act: -0.1700

Data Index: 1347199 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 3.2523. Min Range: -3.2523

Max Act: 2.9631. Min Act: -0.1700

Data Index: 1286598 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 3.2523. Min Range: -3.2523

Max Act: 2.9471. Min Act: -0.1700

Data Index: 173421 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 3.2523. Min Range: -3.2523

Max Act: 2.9409. Min Act: -0.1700

Data Index: 1445451 (Python Code)

Max Activating Token Index: 996