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

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

Neuron 1358 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: 3.6401. Min Range: -3.6401

Max Act: 3.6401. Min Act: -0.1693

Data Index: 170228 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 3.6401. Min Range: -3.6401

Max Act: 3.5743. Min Act: -0.1651

Data Index: 512064 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 3.6401. Min Range: -3.6401

Max Act: 3.5415. Min Act: -0.1700

Data Index: 1373483 (Python Code)

Max Activating Token Index: 51

Text #3

Max Range: 3.6401. Min Range: -3.6401

Max Act: 3.5134. Min Act: -0.1700

Data Index: 391637 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 3.6401. Min Range: -3.6401

Max Act: 3.5027. Min Act: -0.1696

Data Index: 953160 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 3.6401. Min Range: -3.6401

Max Act: 3.4914. Min Act: -0.1698

Data Index: 131923 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 3.6401. Min Range: -3.6401

Max Act: 3.3989. Min Act: -0.1699

Data Index: 1194062 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 3.6401. Min Range: -3.6401

Max Act: 3.4160. Min Act: -0.1697

Data Index: 1318658 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 3.6401. Min Range: -3.6401

Max Act: 3.4095. Min Act: -0.1700

Data Index: 1264331 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 3.6401. Min Range: -3.6401

Max Act: 3.3901. Min Act: -0.1699

Data Index: 1453082 (Python Code)

Max Activating Token Index: 644

Text #10

Max Range: 3.6401. Min Range: -3.6401

Max Act: 3.3835. Min Act: -0.1700

Data Index: 1007223 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 3.6401. Min Range: -3.6401

Max Act: 3.3878. Min Act: -0.1699

Data Index: 805673 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 3.6401. Min Range: -3.6401

Max Act: 3.3711. Min Act: -0.1687

Data Index: 857821 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 3.6401. Min Range: -3.6401

Max Act: 3.3850. Min Act: -0.1696

Data Index: 68121 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 3.6401. Min Range: -3.6401

Max Act: 3.3673. Min Act: -0.1700

Data Index: 1442241 (Python Code)

Max Activating Token Index: 808

Text #15

Max Range: 3.6401. Min Range: -3.6401

Max Act: 3.3673. Min Act: -0.1700

Data Index: 177493 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 3.6401. Min Range: -3.6401

Max Act: 3.3641. Min Act: -0.1700

Data Index: 1508608 (Python Code)

Max Activating Token Index: 196

Text #17

Max Range: 3.6401. Min Range: -3.6401

Max Act: 3.3471. Min Act: -0.1700

Data Index: 909974 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 3.6401. Min Range: -3.6401

Max Act: 3.3431. Min Act: -0.1700

Data Index: 1316409 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 3.6401. Min Range: -3.6401

Max Act: 3.3441. Min Act: -0.1700

Data Index: 1116491 (C4 (Web Text))

Max Activating Token Index: 345