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

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

Neuron 326 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.7019. Min Range: -7.7019

Max Act: 7.7019. Min Act: -0.1700

Data Index: 393407 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 7.7019. Min Range: -7.7019

Max Act: 7.6394. Min Act: -0.1700

Data Index: 748588 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 7.7019. Min Range: -7.7019

Max Act: 7.6394. Min Act: -0.1700

Data Index: 594238 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 7.7019. Min Range: -7.7019

Max Act: 7.6394. Min Act: -0.1700

Data Index: 235219 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 7.7019. Min Range: -7.7019

Max Act: 7.5769. Min Act: -0.1700

Data Index: 693997 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 7.7019. Min Range: -7.7019

Max Act: 7.6394. Min Act: -0.1700

Data Index: 1248892 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 7.7019. Min Range: -7.7019

Max Act: 7.6394. Min Act: -0.1700

Data Index: 1052012 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 7.7019. Min Range: -7.7019

Max Act: 7.5769. Min Act: -0.1700

Data Index: 1040847 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 7.7019. Min Range: -7.7019

Max Act: 7.5144. Min Act: -0.1700

Data Index: 353170 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 7.7019. Min Range: -7.7019

Max Act: 7.4519. Min Act: -0.1700

Data Index: 119753 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 7.7019. Min Range: -7.7019

Max Act: 7.3894. Min Act: -0.1700

Data Index: 192309 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 7.7019. Min Range: -7.7019

Max Act: 7.4519. Min Act: -0.1700

Data Index: 680335 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 7.7019. Min Range: -7.7019

Max Act: 7.5144. Min Act: -0.1700

Data Index: 1098984 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 7.7019. Min Range: -7.7019

Max Act: 7.3894. Min Act: -0.1700

Data Index: 450489 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 7.7019. Min Range: -7.7019

Max Act: 7.3269. Min Act: -0.1700

Data Index: 615573 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 7.7019. Min Range: -7.7019

Max Act: 7.3269. Min Act: -0.1700

Data Index: 395459 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 7.7019. Min Range: -7.7019

Max Act: 7.3269. Min Act: -0.1700

Data Index: 391815 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 7.7019. Min Range: -7.7019

Max Act: 7.3269. Min Act: -0.1700

Data Index: 543337 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 7.7019. Min Range: -7.7019

Max Act: 7.3894. Min Act: -0.1700

Data Index: 1035839 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 7.7019. Min Range: -7.7019

Max Act: 7.3894. Min Act: -0.1700

Data Index: 970495 (C4 (Web Text))

Max Activating Token Index: 639