Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 486 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.9828. Min Act: -0.1700

Data Index: 888354 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.9359. Min Act: -0.1700

Data Index: 344994 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.8890. Min Act: -0.1700

Data Index: 320272 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.8577. Min Act: -0.1700

Data Index: 269243 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.8577. Min Act: -0.1700

Data Index: 809587 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.8264. Min Act: -0.1700

Data Index: 26429 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.8577. Min Act: -0.1700

Data Index: 236969 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.8577. Min Act: -0.1700

Data Index: 1152253 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.8733. Min Act: -0.1700

Data Index: 506057 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.8108. Min Act: -0.1700

Data Index: 820859 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.8108. Min Act: -0.1700

Data Index: 466652 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.7795. Min Act: -0.1700

Data Index: 864303 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.8420. Min Act: -0.1700

Data Index: 389982 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.7951. Min Act: -0.1700

Data Index: 129042 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.8108. Min Act: -0.1700

Data Index: 277356 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.7169. Min Act: -0.1700

Data Index: 691056 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.7795. Min Act: -0.1700

Data Index: 731017 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.7638. Min Act: -0.1700

Data Index: 1206867 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.7795. Min Act: -0.1700

Data Index: 985815 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.7482. Min Act: -0.1700

Data Index: 798551 (C4 (Web Text))

Max Activating Token Index: 492