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

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

Neuron 1366 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: 3.7665. Min Range: -3.7665

Max Act: 3.7665. Min Act: -0.1699

Data Index: 816100 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 3.7665. Min Range: -3.7665

Max Act: 3.6423. Min Act: -0.1691

Data Index: 228926 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 3.7665. Min Range: -3.7665

Max Act: 3.5787. Min Act: -0.1698

Data Index: 68658 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 3.7665. Min Range: -3.7665

Max Act: 3.5241. Min Act: -0.1699

Data Index: 299018 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 3.7665. Min Range: -3.7665

Max Act: 3.5229. Min Act: -0.1699

Data Index: 130896 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 3.7665. Min Range: -3.7665

Max Act: 3.5089. Min Act: -0.1700

Data Index: 427733 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 3.7665. Min Range: -3.7665

Max Act: 3.5533. Min Act: -0.1700

Data Index: 852509 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 3.7665. Min Range: -3.7665

Max Act: 3.5006. Min Act: -0.1700

Data Index: 406051 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 3.7665. Min Range: -3.7665

Max Act: 3.4820. Min Act: -0.1697

Data Index: 483941 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 3.7665. Min Range: -3.7665

Max Act: 3.4423. Min Act: -0.1700

Data Index: 456556 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 3.7665. Min Range: -3.7665

Max Act: 3.4739. Min Act: -0.1678

Data Index: 923322 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 3.7665. Min Range: -3.7665

Max Act: 3.4448. Min Act: -0.1641

Data Index: 1214684 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 3.7665. Min Range: -3.7665

Max Act: 3.4402. Min Act: -0.1699

Data Index: 753584 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 3.7665. Min Range: -3.7665

Max Act: 3.4708. Min Act: -0.1700

Data Index: 288240 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 3.7665. Min Range: -3.7665

Max Act: 3.4496. Min Act: -0.1623

Data Index: 1117934 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 3.7665. Min Range: -3.7665

Max Act: 3.4316. Min Act: -0.1698

Data Index: 483060 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 3.7665. Min Range: -3.7665

Max Act: 3.4192. Min Act: -0.1699

Data Index: 652600 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 3.7665. Min Range: -3.7665

Max Act: 3.4189. Min Act: -0.1700

Data Index: 309196 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 3.7665. Min Range: -3.7665

Max Act: 3.4138. Min Act: -0.1700

Data Index: 10600 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 3.7665. Min Range: -3.7665

Max Act: 3.4373. Min Act: -0.1700

Data Index: 1069504 (C4 (Web Text))

Max Activating Token Index: 900