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

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

Neuron 402 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: 3.6120. Min Range: -3.6120

Max Act: 3.5942. Min Act: -0.1700

Data Index: 1082780 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.6120. Min Act: -0.1700

Data Index: 1095647 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.4940. Min Act: -0.1700

Data Index: 628638 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.4702. Min Act: -0.1700

Data Index: 1064983 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.4523. Min Act: -0.1700

Data Index: 610328 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.4587. Min Act: -0.1700

Data Index: 563608 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.4497. Min Act: -0.1700

Data Index: 1512925 (Python Code)

Max Activating Token Index: 780

Text #7

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.4248. Min Act: -0.1700

Data Index: 158609 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.4406. Min Act: -0.1700

Data Index: 1382701 (Python Code)

Max Activating Token Index: 206

Text #9

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.4289. Min Act: -0.1700

Data Index: 1143995 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.4184. Min Act: -0.1700

Data Index: 830942 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.4176. Min Act: -0.1700

Data Index: 1409959 (Python Code)

Max Activating Token Index: 423

Text #12

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.4112. Min Act: -0.1700

Data Index: 1421081 (Python Code)

Max Activating Token Index: 446

Text #13

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.4193. Min Act: -0.1700

Data Index: 986982 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.4037. Min Act: -0.1700

Data Index: 1612616 (Python Code)

Max Activating Token Index: 501

Text #15

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.3869. Min Act: -0.1700

Data Index: 1430590 (Python Code)

Max Activating Token Index: 613

Text #16

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.3883. Min Act: -0.1700

Data Index: 1655652 (Python Code)

Max Activating Token Index: 119

Text #17

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.3940. Min Act: -0.1700

Data Index: 835947 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.3908. Min Act: -0.1700

Data Index: 39874 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.3856. Min Act: -0.1700

Data Index: 482805 (C4 (Web Text))

Max Activating Token Index: 1022