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

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

Neuron 341 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: 4.1886. Min Range: -4.1886

Max Act: 4.1583. Min Act: -0.1700

Data Index: 1315503 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 4.1886. Min Range: -4.1886

Max Act: 4.1886. Min Act: -0.1700

Data Index: 986343 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 4.1886. Min Range: -4.1886

Max Act: 4.1741. Min Act: -0.1700

Data Index: 175344 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 4.1886. Min Range: -4.1886

Max Act: 4.1537. Min Act: -0.1700

Data Index: 1257311 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 4.1886. Min Range: -4.1886

Max Act: 4.1123. Min Act: -0.1700

Data Index: 85657 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 4.1886. Min Range: -4.1886

Max Act: 4.0827. Min Act: -0.1700

Data Index: 533399 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 4.1886. Min Range: -4.1886

Max Act: 4.0631. Min Act: -0.1700

Data Index: 950667 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 4.1886. Min Range: -4.1886

Max Act: 4.0639. Min Act: -0.1700

Data Index: 425462 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 4.1886. Min Range: -4.1886

Max Act: 4.0542. Min Act: -0.1700

Data Index: 1119411 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 4.1886. Min Range: -4.1886

Max Act: 4.0404. Min Act: -0.1700

Data Index: 1279870 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 4.1886. Min Range: -4.1886

Max Act: 4.0423. Min Act: -0.1700

Data Index: 1058870 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 4.1886. Min Range: -4.1886

Max Act: 3.9995. Min Act: -0.1700

Data Index: 164369 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 4.1886. Min Range: -4.1886

Max Act: 3.9826. Min Act: -0.1700

Data Index: 1350033 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 4.1886. Min Range: -4.1886

Max Act: 4.0097. Min Act: -0.1700

Data Index: 1130984 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 4.1886. Min Range: -4.1886

Max Act: 3.9700. Min Act: -0.1700

Data Index: 1122047 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 4.1886. Min Range: -4.1886

Max Act: 3.9703. Min Act: -0.1700

Data Index: 425872 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 4.1886. Min Range: -4.1886

Max Act: 3.9593. Min Act: -0.1700

Data Index: 108444 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 4.1886. Min Range: -4.1886

Max Act: 3.9672. Min Act: -0.1700

Data Index: 974939 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 4.1886. Min Range: -4.1886

Max Act: 3.9233. Min Act: -0.1700

Data Index: 46515 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 4.1886. Min Range: -4.1886

Max Act: 3.9185. Min Act: -0.1700

Data Index: 38043 (C4 (Web Text))

Max Activating Token Index: 721