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

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

Neuron 1914 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: 3.3652. Min Range: -3.3652

Max Act: 3.3652. Min Act: -0.1700

Data Index: 621830 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 3.3652. Min Range: -3.3652

Max Act: 3.3321. Min Act: -0.1700

Data Index: 390045 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 3.3652. Min Range: -3.3652

Max Act: 3.3068. Min Act: -0.1700

Data Index: 916312 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 3.3652. Min Range: -3.3652

Max Act: 3.3058. Min Act: -0.1700

Data Index: 377576 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 3.3652. Min Range: -3.3652

Max Act: 3.3119. Min Act: -0.1700

Data Index: 1206095 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 3.3652. Min Range: -3.3652

Max Act: 3.2616. Min Act: -0.1700

Data Index: 556113 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 3.3652. Min Range: -3.3652

Max Act: 3.2315. Min Act: -0.1700

Data Index: 188768 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 3.3652. Min Range: -3.3652

Max Act: 3.2412. Min Act: -0.1700

Data Index: 225348 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 3.3652. Min Range: -3.3652

Max Act: 3.2445. Min Act: -0.1700

Data Index: 366577 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 3.3652. Min Range: -3.3652

Max Act: 3.2349. Min Act: -0.1700

Data Index: 810802 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 3.3652. Min Range: -3.3652

Max Act: 3.2406. Min Act: -0.1700

Data Index: 63272 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 3.3652. Min Range: -3.3652

Max Act: 3.2408. Min Act: -0.1700

Data Index: 627037 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 3.3652. Min Range: -3.3652

Max Act: 3.2273. Min Act: -0.1700

Data Index: 808545 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 3.3652. Min Range: -3.3652

Max Act: 3.2212. Min Act: -0.1700

Data Index: 598247 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 3.3652. Min Range: -3.3652

Max Act: 3.2187. Min Act: -0.1700

Data Index: 388252 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 3.3652. Min Range: -3.3652

Max Act: 3.2008. Min Act: -0.1700

Data Index: 1120270 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 3.3652. Min Range: -3.3652

Max Act: 3.1961. Min Act: -0.1700

Data Index: 1091950 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 3.3652. Min Range: -3.3652

Max Act: 3.1962. Min Act: -0.1700

Data Index: 469965 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 3.3652. Min Range: -3.3652

Max Act: 3.1614. Min Act: -0.1700

Data Index: 1498881 (Python Code)

Max Activating Token Index: 780

Text #19

Max Range: 3.3652. Min Range: -3.3652

Max Act: 3.1746. Min Act: -0.1700

Data Index: 237248 (C4 (Web Text))

Max Activating Token Index: 71