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

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

Neuron 1473 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: 4.3883. Min Range: -4.3883

Max Act: 4.3883. Min Act: -0.1700

Data Index: 1458446 (Python Code)

Max Activating Token Index: 285

Text #1

Max Range: 4.3883. Min Range: -4.3883

Max Act: 4.1578. Min Act: -0.1699

Data Index: 810063 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 4.3883. Min Range: -4.3883

Max Act: 4.1365. Min Act: -0.1700

Data Index: 1586400 (Python Code)

Max Activating Token Index: 476

Text #3

Max Range: 4.3883. Min Range: -4.3883

Max Act: 4.1115. Min Act: -0.1700

Data Index: 511463 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 4.3883. Min Range: -4.3883

Max Act: 4.0910. Min Act: -0.1700

Data Index: 1531420 (Python Code)

Max Activating Token Index: 470

Text #5

Max Range: 4.3883. Min Range: -4.3883

Max Act: 4.0804. Min Act: -0.1700

Data Index: 1596694 (Python Code)

Max Activating Token Index: 873

Text #6

Max Range: 4.3883. Min Range: -4.3883

Max Act: 4.1203. Min Act: -0.1693

Data Index: 320126 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 4.3883. Min Range: -4.3883

Max Act: 4.0306. Min Act: -0.1694

Data Index: 1601325 (Python Code)

Max Activating Token Index: 410

Text #8

Max Range: 4.3883. Min Range: -4.3883

Max Act: 4.0566. Min Act: -0.1681

Data Index: 947910 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 4.3883. Min Range: -4.3883

Max Act: 3.9707. Min Act: -0.1700

Data Index: 1583767 (Python Code)

Max Activating Token Index: 760

Text #10

Max Range: 4.3883. Min Range: -4.3883

Max Act: 3.9490. Min Act: -0.1700

Data Index: 1372747 (Python Code)

Max Activating Token Index: 329

Text #11

Max Range: 4.3883. Min Range: -4.3883

Max Act: 3.9588. Min Act: -0.1692

Data Index: 1611454 (Python Code)

Max Activating Token Index: 623

Text #12

Max Range: 4.3883. Min Range: -4.3883

Max Act: 3.9821. Min Act: -0.1700

Data Index: 1191864 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 4.3883. Min Range: -4.3883

Max Act: 3.9827. Min Act: -0.1700

Data Index: 83027 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 4.3883. Min Range: -4.3883

Max Act: 3.9322. Min Act: -0.1668

Data Index: 783652 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 4.3883. Min Range: -4.3883

Max Act: 3.8940. Min Act: -0.1700

Data Index: 1477697 (Python Code)

Max Activating Token Index: 84

Text #16

Max Range: 4.3883. Min Range: -4.3883

Max Act: 3.9134. Min Act: -0.1700

Data Index: 1454375 (Python Code)

Max Activating Token Index: 1011

Text #17

Max Range: 4.3883. Min Range: -4.3883

Max Act: 3.9080. Min Act: -0.1700

Data Index: 1420895 (Python Code)

Max Activating Token Index: 89

Text #18

Max Range: 4.3883. Min Range: -4.3883

Max Act: 3.9062. Min Act: -0.1699

Data Index: 169615 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 4.3883. Min Range: -4.3883

Max Act: 3.8936. Min Act: -0.1700

Data Index: 945669 (C4 (Web Text))

Max Activating Token Index: 726