Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 766 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 7.1689. Min Range: -7.1689

Max Act: 7.1689. Min Act: -0.1699

Data Index: 184857 (C4 (Web Text))

Max Activating Token Index: 299

Text #1

Max Range: 7.1689. Min Range: -7.1689

Max Act: 7.0752. Min Act: -0.1700

Data Index: 81561 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 7.1689. Min Range: -7.1689

Max Act: 6.8252. Min Act: -0.1700

Data Index: 176174 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 7.1689. Min Range: -7.1689

Max Act: 6.7314. Min Act: -0.1700

Data Index: 549626 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 7.1689. Min Range: -7.1689

Max Act: 6.4502. Min Act: -0.1700

Data Index: 860708 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 7.1689. Min Range: -7.1689

Max Act: 6.4814. Min Act: -0.1700

Data Index: 785825 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 7.1689. Min Range: -7.1689

Max Act: 6.4502. Min Act: -0.1700

Data Index: 365679 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 7.1689. Min Range: -7.1689

Max Act: 6.3564. Min Act: -0.1700

Data Index: 837132 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 7.1689. Min Range: -7.1689

Max Act: 6.3877. Min Act: -0.1700

Data Index: 387346 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 7.1689. Min Range: -7.1689

Max Act: 6.4502. Min Act: -0.1700

Data Index: 106310 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 7.1689. Min Range: -7.1689

Max Act: 6.3877. Min Act: -0.1700

Data Index: 384695 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 7.1689. Min Range: -7.1689

Max Act: 6.3252. Min Act: -0.1700

Data Index: 957387 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 7.1689. Min Range: -7.1689

Max Act: 6.3877. Min Act: -0.1698

Data Index: 1035067 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 7.1689. Min Range: -7.1689

Max Act: 6.2627. Min Act: -0.1700

Data Index: 30670 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 7.1689. Min Range: -7.1689

Max Act: 6.2939. Min Act: -0.1700

Data Index: 1223819 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 7.1689. Min Range: -7.1689

Max Act: 6.3252. Min Act: -0.1700

Data Index: 733984 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 7.1689. Min Range: -7.1689

Max Act: 6.2939. Min Act: -0.1700

Data Index: 615105 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 7.1689. Min Range: -7.1689

Max Act: 6.2939. Min Act: -0.1700

Data Index: 601631 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 7.1689. Min Range: -7.1689

Max Act: 6.3252. Min Act: -0.1700

Data Index: 962903 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 7.1689. Min Range: -7.1689

Max Act: 6.2939. Min Act: -0.1700

Data Index: 453611 (C4 (Web Text))

Max Activating Token Index: 834