Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 768 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.4456. Min Range: -5.4456

Max Act: 5.4456. Min Act: -0.1700

Data Index: 1203388 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 5.4456. Min Range: -5.4456

Max Act: 5.3519. Min Act: -0.1700

Data Index: 1061255 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 5.4456. Min Range: -5.4456

Max Act: 5.2581. Min Act: -0.1700

Data Index: 436732 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 5.4456. Min Range: -5.4456

Max Act: 5.1644. Min Act: -0.1700

Data Index: 763282 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 5.4456. Min Range: -5.4456

Max Act: 5.1019. Min Act: -0.1700

Data Index: 465042 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 5.4456. Min Range: -5.4456

Max Act: 5.0706. Min Act: -0.1700

Data Index: 738694 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 5.4456. Min Range: -5.4456

Max Act: 5.0706. Min Act: -0.1700

Data Index: 260330 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 5.4456. Min Range: -5.4456

Max Act: 5.0394. Min Act: -0.1700

Data Index: 716020 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 5.4456. Min Range: -5.4456

Max Act: 4.9769. Min Act: -0.1700

Data Index: 1244054 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 5.4456. Min Range: -5.4456

Max Act: 5.0081. Min Act: -0.1700

Data Index: 820409 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 5.4456. Min Range: -5.4456

Max Act: 4.9769. Min Act: -0.1700

Data Index: 1002233 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 5.4456. Min Range: -5.4456

Max Act: 5.0081. Min Act: -0.1700

Data Index: 31960 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 5.4456. Min Range: -5.4456

Max Act: 4.9456. Min Act: -0.1700

Data Index: 234340 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 5.4456. Min Range: -5.4456

Max Act: 4.9456. Min Act: -0.1700

Data Index: 469373 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 5.4456. Min Range: -5.4456

Max Act: 4.8831. Min Act: -0.1700

Data Index: 570615 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 5.4456. Min Range: -5.4456

Max Act: 4.9144. Min Act: -0.1700

Data Index: 739307 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 5.4456. Min Range: -5.4456

Max Act: 4.8519. Min Act: -0.1700

Data Index: 1045022 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 5.4456. Min Range: -5.4456

Max Act: 4.8519. Min Act: -0.1700

Data Index: 566967 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 5.4456. Min Range: -5.4456

Max Act: 4.8519. Min Act: -0.1700

Data Index: 864609 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 5.4456. Min Range: -5.4456

Max Act: 4.8206. Min Act: -0.1700

Data Index: 1198766 (C4 (Web Text))

Max Activating Token Index: 677