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

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

Neuron 166 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: 3.2287. Min Range: -3.2287

Max Act: 3.2287. Min Act: -0.1699

Data Index: 1015783 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 3.2287. Min Range: -3.2287

Max Act: 3.2177. Min Act: -0.1700

Data Index: 187414 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 3.2287. Min Range: -3.2287

Max Act: 3.1607. Min Act: -0.1700

Data Index: 535594 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 3.2287. Min Range: -3.2287

Max Act: 3.1004. Min Act: -0.1700

Data Index: 62159 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 3.2287. Min Range: -3.2287

Max Act: 3.0892. Min Act: -0.1699

Data Index: 864236 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 3.2287. Min Range: -3.2287

Max Act: 3.0908. Min Act: -0.1700

Data Index: 991642 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 3.2287. Min Range: -3.2287

Max Act: 3.0892. Min Act: -0.1700

Data Index: 657190 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 3.2287. Min Range: -3.2287

Max Act: 3.0631. Min Act: -0.1700

Data Index: 131952 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 3.2287. Min Range: -3.2287

Max Act: 3.0726. Min Act: -0.1700

Data Index: 695346 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 3.2287. Min Range: -3.2287

Max Act: 3.0831. Min Act: -0.1700

Data Index: 1065185 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 3.2287. Min Range: -3.2287

Max Act: 3.0689. Min Act: -0.1700

Data Index: 552623 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 3.2287. Min Range: -3.2287

Max Act: 3.0410. Min Act: -0.1700

Data Index: 218767 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 3.2287. Min Range: -3.2287

Max Act: 3.0443. Min Act: -0.1700

Data Index: 912807 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 3.2287. Min Range: -3.2287

Max Act: 3.0522. Min Act: -0.1700

Data Index: 985308 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 3.2287. Min Range: -3.2287

Max Act: 3.0537. Min Act: -0.1700

Data Index: 352728 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 3.2287. Min Range: -3.2287

Max Act: 3.0493. Min Act: -0.1700

Data Index: 830121 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 3.2287. Min Range: -3.2287

Max Act: 3.0321. Min Act: -0.1700

Data Index: 89180 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 3.2287. Min Range: -3.2287

Max Act: 3.0444. Min Act: -0.1700

Data Index: 174374 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 3.2287. Min Range: -3.2287

Max Act: 3.0319. Min Act: -0.1699

Data Index: 263583 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 3.2287. Min Range: -3.2287

Max Act: 3.0390. Min Act: -0.1700

Data Index: 388701 (C4 (Web Text))

Max Activating Token Index: 132