Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 772 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 6.1849. Min Range: -6.1849

Max Act: 6.1849. Min Act: -0.1509

Data Index: 1069050 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 6.1849. Min Range: -6.1849

Max Act: 6.1638. Min Act: -0.1699

Data Index: 1567463 (Python Code)

Max Activating Token Index: 206

Text #2

Max Range: 6.1849. Min Range: -6.1849

Max Act: 6.1451. Min Act: -0.1699

Data Index: 1652003 (Python Code)

Max Activating Token Index: 188

Text #3

Max Range: 6.1849. Min Range: -6.1849

Max Act: 6.1176. Min Act: -0.1700

Data Index: 238585 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 6.1849. Min Range: -6.1849

Max Act: 6.1016. Min Act: -0.1700

Data Index: 294622 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 6.1849. Min Range: -6.1849

Max Act: 6.1203. Min Act: -0.1700

Data Index: 1319016 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 6.1849. Min Range: -6.1849

Max Act: 6.0948. Min Act: -0.1699

Data Index: 177169 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 6.1849. Min Range: -6.1849

Max Act: 6.0537. Min Act: -0.1700

Data Index: 562761 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 6.1849. Min Range: -6.1849

Max Act: 6.0418. Min Act: -0.1700

Data Index: 1378756 (Python Code)

Max Activating Token Index: 735

Text #9

Max Range: 6.1849. Min Range: -6.1849

Max Act: 6.0364. Min Act: -0.1700

Data Index: 1579001 (Python Code)

Max Activating Token Index: 765

Text #10

Max Range: 6.1849. Min Range: -6.1849

Max Act: 6.0240. Min Act: -0.1700

Data Index: 1600205 (Python Code)

Max Activating Token Index: 282

Text #11

Max Range: 6.1849. Min Range: -6.1849

Max Act: 6.0290. Min Act: -0.1700

Data Index: 1393182 (Python Code)

Max Activating Token Index: 306

Text #12

Max Range: 6.1849. Min Range: -6.1849

Max Act: 6.0253. Min Act: -0.1700

Data Index: 1545671 (Python Code)

Max Activating Token Index: 605

Text #13

Max Range: 6.1849. Min Range: -6.1849

Max Act: 5.9715. Min Act: -0.1700

Data Index: 1427727 (Python Code)

Max Activating Token Index: 856

Text #14

Max Range: 6.1849. Min Range: -6.1849

Max Act: 5.9780. Min Act: -0.1700

Data Index: 1448250 (Python Code)

Max Activating Token Index: 587

Text #15

Max Range: 6.1849. Min Range: -6.1849

Max Act: 5.9835. Min Act: -0.1700

Data Index: 1298837 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 6.1849. Min Range: -6.1849

Max Act: 5.9737. Min Act: -0.1696

Data Index: 913322 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 6.1849. Min Range: -6.1849

Max Act: 5.9689. Min Act: -0.1700

Data Index: 194834 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 6.1849. Min Range: -6.1849

Max Act: 5.9550. Min Act: -0.1700

Data Index: 306463 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 6.1849. Min Range: -6.1849

Max Act: 5.9626. Min Act: -0.1700

Data Index: 1610465 (Python Code)

Max Activating Token Index: 836