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

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

Neuron 1749 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: 3.9773. Min Range: -3.9773

Max Act: 3.9773. Min Act: -0.1700

Data Index: 643676 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.9460. Min Act: -0.1700

Data Index: 793217 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.9304. Min Act: -0.1700

Data Index: 1152850 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.8835. Min Act: -0.1700

Data Index: 1016718 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.7427. Min Act: -0.1700

Data Index: 794810 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.7271. Min Act: -0.1700

Data Index: 688840 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.6958. Min Act: -0.1700

Data Index: 133387 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.6801. Min Act: -0.1700

Data Index: 940929 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.6332. Min Act: -0.1700

Data Index: 102360 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.6801. Min Act: -0.1700

Data Index: 16442 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.6801. Min Act: -0.1700

Data Index: 697442 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.6645. Min Act: -0.1699

Data Index: 266330 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.6645. Min Act: -0.1700

Data Index: 1296285 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.6488. Min Act: -0.1700

Data Index: 1213966 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.6488. Min Act: -0.1700

Data Index: 832938 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.6175. Min Act: -0.1700

Data Index: 622799 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.6332. Min Act: -0.1700

Data Index: 1215675 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.6018. Min Act: -0.1700

Data Index: 908602 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.6175. Min Act: -0.1700

Data Index: 236092 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.6332. Min Act: -0.1700

Data Index: 670342 (C4 (Web Text))

Max Activating Token Index: 861