Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1703 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.6331. Min Act: -0.1700

Data Index: 462394 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.5705. Min Act: -0.1700

Data Index: 463014 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.5391. Min Act: -0.1700

Data Index: 772138 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.5391. Min Act: -0.1700

Data Index: 338168 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.4765. Min Act: -0.1700

Data Index: 957491 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.5391. Min Act: -0.1700

Data Index: 377544 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.4765. Min Act: -0.1700

Data Index: 532597 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.4765. Min Act: -0.1700

Data Index: 1078262 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.4765. Min Act: -0.1700

Data Index: 541653 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.4765. Min Act: -0.1700

Data Index: 779951 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.4451. Min Act: -0.1700

Data Index: 162852 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.4138. Min Act: -0.1700

Data Index: 11420 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.4451. Min Act: -0.1700

Data Index: 398712 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.4765. Min Act: -0.1700

Data Index: 13858 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.4451. Min Act: -0.1700

Data Index: 537247 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.4138. Min Act: -0.1700

Data Index: 1011221 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.4138. Min Act: -0.1700

Data Index: 1061856 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.4138. Min Act: -0.1700

Data Index: 1242804 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.4451. Min Act: -0.1700

Data Index: 1299118 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.4138. Min Act: -0.1700

Data Index: 1340354 (C4 (Web Text))

Max Activating Token Index: 184