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

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

Neuron 1925 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: 4.3157. Min Range: -4.3157

Max Act: 4.3157. Min Act: -0.1700

Data Index: 700302 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 4.3157. Min Range: -4.3157

Max Act: 4.0763. Min Act: -0.1699

Data Index: 404459 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.9746. Min Act: -0.1700

Data Index: 128298 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.9507. Min Act: -0.1700

Data Index: 142488 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.9611. Min Act: -0.1699

Data Index: 259766 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.9482. Min Act: -0.1699

Data Index: 786981 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.9372. Min Act: -0.1699

Data Index: 1213822 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.9260. Min Act: -0.1700

Data Index: 937454 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.9105. Min Act: -0.1700

Data Index: 31663 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.9190. Min Act: -0.1700

Data Index: 349282 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.8693. Min Act: -0.1700

Data Index: 1289593 (C4 (Web Text))

Max Activating Token Index: 1021

Text #11

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.8820. Min Act: -0.1700

Data Index: 1098052 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.8582. Min Act: -0.1700

Data Index: 403463 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.8404. Min Act: -0.1695

Data Index: 849638 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.8325. Min Act: -0.1700

Data Index: 1345448 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.8154. Min Act: -0.1698

Data Index: 935299 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.7900. Min Act: -0.1700

Data Index: 674711 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.7925. Min Act: -0.1700

Data Index: 110534 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.7906. Min Act: -0.1700

Data Index: 650753 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.7818. Min Act: -0.1700

Data Index: 902039 (C4 (Web Text))

Max Activating Token Index: 80