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

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

Neuron 4 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: 3.9548. Min Range: -3.9548

Max Act: 3.9236. Min Act: -0.1700

Data Index: 817446 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 3.9548. Min Range: -3.9548

Max Act: 3.9548. Min Act: -0.1700

Data Index: 1050091 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 3.9548. Min Range: -3.9548

Max Act: 3.8923. Min Act: -0.1700

Data Index: 160217 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 3.9548. Min Range: -3.9548

Max Act: 3.8767. Min Act: -0.1700

Data Index: 263616 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 3.9548. Min Range: -3.9548

Max Act: 3.8298. Min Act: -0.1700

Data Index: 1042387 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 3.9548. Min Range: -3.9548

Max Act: 3.8141. Min Act: -0.1700

Data Index: 710962 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 3.9548. Min Range: -3.9548

Max Act: 3.7828. Min Act: -0.1700

Data Index: 4681 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 3.9548. Min Range: -3.9548

Max Act: 3.7515. Min Act: -0.1700

Data Index: 1030635 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 3.9548. Min Range: -3.9548

Max Act: 3.8141. Min Act: -0.1700

Data Index: 455100 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 3.9548. Min Range: -3.9548

Max Act: 3.6890. Min Act: -0.1700

Data Index: 464240 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 3.9548. Min Range: -3.9548

Max Act: 3.7515. Min Act: -0.1700

Data Index: 377751 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 3.9548. Min Range: -3.9548

Max Act: 3.7046. Min Act: -0.1700

Data Index: 132758 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 3.9548. Min Range: -3.9548

Max Act: 3.7046. Min Act: -0.1700

Data Index: 28946 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 3.9548. Min Range: -3.9548

Max Act: 3.6577. Min Act: -0.1700

Data Index: 542740 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 3.9548. Min Range: -3.9548

Max Act: 3.6733. Min Act: -0.1700

Data Index: 166423 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 3.9548. Min Range: -3.9548

Max Act: 3.6264. Min Act: -0.1700

Data Index: 681900 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 3.9548. Min Range: -3.9548

Max Act: 3.6420. Min Act: -0.1700

Data Index: 228310 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 3.9548. Min Range: -3.9548

Max Act: 3.6577. Min Act: -0.1700

Data Index: 1234597 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 3.9548. Min Range: -3.9548

Max Act: 3.6577. Min Act: -0.1700

Data Index: 1258239 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 3.9548. Min Range: -3.9548

Max Act: 3.6107. Min Act: -0.1700

Data Index: 555859 (C4 (Web Text))

Max Activating Token Index: 13