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

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

Neuron 1005 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: 3.8317. Min Range: -3.8317

Max Act: 3.8317. Min Act: -0.1700

Data Index: 1205948 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 3.8317. Min Range: -3.8317

Max Act: 3.8004. Min Act: -0.1700

Data Index: 1110066 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 3.8317. Min Range: -3.8317

Max Act: 3.7065. Min Act: -0.1700

Data Index: 708894 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 3.8317. Min Range: -3.8317

Max Act: 3.6909. Min Act: -0.1685

Data Index: 647433 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 3.8317. Min Range: -3.8317

Max Act: 3.7065. Min Act: -0.1699

Data Index: 1300181 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 3.8317. Min Range: -3.8317

Max Act: 3.6752. Min Act: -0.1700

Data Index: 556270 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 3.8317. Min Range: -3.8317

Max Act: 3.6752. Min Act: -0.1700

Data Index: 1131026 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 3.8317. Min Range: -3.8317

Max Act: 3.6752. Min Act: -0.1700

Data Index: 901603 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 3.8317. Min Range: -3.8317

Max Act: 3.6596. Min Act: -0.1697

Data Index: 921826 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 3.8317. Min Range: -3.8317

Max Act: 3.6596. Min Act: -0.1700

Data Index: 1276892 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 3.8317. Min Range: -3.8317

Max Act: 3.6283. Min Act: -0.1700

Data Index: 1612638 (Python Code)

Max Activating Token Index: 187

Text #11

Max Range: 3.8317. Min Range: -3.8317

Max Act: 3.6439. Min Act: -0.1700

Data Index: 1398337 (Python Code)

Max Activating Token Index: 873

Text #12

Max Range: 3.8317. Min Range: -3.8317

Max Act: 3.6126. Min Act: -0.1700

Data Index: 461050 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 3.8317. Min Range: -3.8317

Max Act: 3.6283. Min Act: -0.1700

Data Index: 267994 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 3.8317. Min Range: -3.8317

Max Act: 3.6283. Min Act: -0.1700

Data Index: 267996 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 3.8317. Min Range: -3.8317

Max Act: 3.6283. Min Act: -0.1657

Data Index: 1137100 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 3.8317. Min Range: -3.8317

Max Act: 3.6126. Min Act: -0.1700

Data Index: 1057831 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 3.8317. Min Range: -3.8317

Max Act: 3.6126. Min Act: -0.1700

Data Index: 209075 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 3.8317. Min Range: -3.8317

Max Act: 3.6126. Min Act: -0.1697

Data Index: 531125 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 3.8317. Min Range: -3.8317

Max Act: 3.5656. Min Act: -0.1700

Data Index: 1094657 (C4 (Web Text))

Max Activating Token Index: 51