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

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

Neuron 764 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: 3.0671. Min Range: -3.0671

Max Act: 3.0671. Min Act: -0.1700

Data Index: 1130713 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 3.0671. Min Range: -3.0671

Max Act: 2.9400. Min Act: -0.1700

Data Index: 716096 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 3.0671. Min Range: -3.0671

Max Act: 2.9170. Min Act: -0.1699

Data Index: 703300 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 3.0671. Min Range: -3.0671

Max Act: 2.8897. Min Act: -0.1700

Data Index: 723785 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 3.0671. Min Range: -3.0671

Max Act: 2.8881. Min Act: -0.1698

Data Index: 1097753 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 3.0671. Min Range: -3.0671

Max Act: 2.8539. Min Act: -0.1615

Data Index: 449187 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 3.0671. Min Range: -3.0671

Max Act: 2.8424. Min Act: -0.1699

Data Index: 1396768 (Python Code)

Max Activating Token Index: 55

Text #7

Max Range: 3.0671. Min Range: -3.0671

Max Act: 2.8360. Min Act: -0.1700

Data Index: 506716 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 3.0671. Min Range: -3.0671

Max Act: 2.8336. Min Act: -0.1700

Data Index: 512520 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 3.0671. Min Range: -3.0671

Max Act: 2.8199. Min Act: -0.1699

Data Index: 1526231 (Python Code)

Max Activating Token Index: 367

Text #10

Max Range: 3.0671. Min Range: -3.0671

Max Act: 2.7771. Min Act: -0.1615

Data Index: 567376 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 3.0671. Min Range: -3.0671

Max Act: 2.7718. Min Act: -0.1700

Data Index: 811014 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 3.0671. Min Range: -3.0671

Max Act: 2.7651. Min Act: -0.1699

Data Index: 1426913 (Python Code)

Max Activating Token Index: 715

Text #13

Max Range: 3.0671. Min Range: -3.0671

Max Act: 2.7503. Min Act: -0.1700

Data Index: 1547171 (Python Code)

Max Activating Token Index: 158

Text #14

Max Range: 3.0671. Min Range: -3.0671

Max Act: 2.7485. Min Act: -0.1700

Data Index: 739764 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 3.0671. Min Range: -3.0671

Max Act: 2.7367. Min Act: -0.1679

Data Index: 400126 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 3.0671. Min Range: -3.0671

Max Act: 2.7313. Min Act: -0.1700

Data Index: 281497 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 3.0671. Min Range: -3.0671

Max Act: 2.7520. Min Act: -0.1696

Data Index: 834049 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 3.0671. Min Range: -3.0671

Max Act: 2.7575. Min Act: -0.1699

Data Index: 534492 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 3.0671. Min Range: -3.0671

Max Act: 2.7067. Min Act: -0.1700

Data Index: 988036 (C4 (Web Text))

Max Activating Token Index: 774