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

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

Neuron 2028 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: 3.7513. Min Range: -3.7513

Max Act: 3.7513. Min Act: -0.1700

Data Index: 442483 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 3.7513. Min Range: -3.7513

Max Act: 3.7056. Min Act: -0.1700

Data Index: 169171 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 3.7513. Min Range: -3.7513

Max Act: 3.6107. Min Act: -0.1700

Data Index: 997424 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 3.7513. Min Range: -3.7513

Max Act: 3.5933. Min Act: -0.1700

Data Index: 40229 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 3.7513. Min Range: -3.7513

Max Act: 3.5696. Min Act: -0.1700

Data Index: 383805 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 3.7513. Min Range: -3.7513

Max Act: 3.5775. Min Act: -0.1700

Data Index: 191794 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 3.7513. Min Range: -3.7513

Max Act: 3.5636. Min Act: -0.1700

Data Index: 848849 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 3.7513. Min Range: -3.7513

Max Act: 3.5607. Min Act: -0.1700

Data Index: 767375 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 3.7513. Min Range: -3.7513

Max Act: 3.5572. Min Act: -0.1700

Data Index: 701627 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 3.7513. Min Range: -3.7513

Max Act: 3.5389. Min Act: -0.1700

Data Index: 962124 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 3.7513. Min Range: -3.7513

Max Act: 3.5325. Min Act: -0.1700

Data Index: 74552 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 3.7513. Min Range: -3.7513

Max Act: 3.5254. Min Act: -0.1700

Data Index: 146496 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 3.7513. Min Range: -3.7513

Max Act: 3.5232. Min Act: -0.1700

Data Index: 957794 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 3.7513. Min Range: -3.7513

Max Act: 3.5392. Min Act: -0.1700

Data Index: 686057 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 3.7513. Min Range: -3.7513

Max Act: 3.5169. Min Act: -0.1700

Data Index: 1025989 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 3.7513. Min Range: -3.7513

Max Act: 3.5216. Min Act: -0.1700

Data Index: 547872 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 3.7513. Min Range: -3.7513

Max Act: 3.5089. Min Act: -0.1700

Data Index: 550694 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 3.7513. Min Range: -3.7513

Max Act: 3.5164. Min Act: -0.1700

Data Index: 990526 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 3.7513. Min Range: -3.7513

Max Act: 3.4841. Min Act: -0.1700

Data Index: 264763 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 3.7513. Min Range: -3.7513

Max Act: 3.4838. Min Act: -0.1700

Data Index: 986628 (C4 (Web Text))

Max Activating Token Index: 115