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

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

Neuron 811 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: 3.7750. Min Range: -3.7750

Max Act: 3.7750. Min Act: -0.1666

Data Index: 1426499 (Python Code)

Max Activating Token Index: 921

Text #1

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.7100. Min Act: -0.1666

Data Index: 800260 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.7139. Min Act: -0.1698

Data Index: 1488291 (Python Code)

Max Activating Token Index: 431

Text #3

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.7221. Min Act: -0.1700

Data Index: 1028293 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.7302. Min Act: -0.1699

Data Index: 369328 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.6929. Min Act: -0.1666

Data Index: 1579891 (Python Code)

Max Activating Token Index: 390

Text #6

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.6023. Min Act: -0.1699

Data Index: 1248751 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.6353. Min Act: -0.1686

Data Index: 1592328 (Python Code)

Max Activating Token Index: 182

Text #8

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.5648. Min Act: -0.1666

Data Index: 839225 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.5464. Min Act: -0.1698

Data Index: 1588682 (Python Code)

Max Activating Token Index: 831

Text #10

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.5656. Min Act: -0.1678

Data Index: 1565365 (Python Code)

Max Activating Token Index: 816

Text #11

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.5464. Min Act: -0.1682

Data Index: 1582997 (Python Code)

Max Activating Token Index: 518

Text #12

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.5470. Min Act: -0.1700

Data Index: 1536507 (Python Code)

Max Activating Token Index: 605

Text #13

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.5171. Min Act: -0.1700

Data Index: 694318 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.4872. Min Act: -0.1699

Data Index: 561489 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.4869. Min Act: -0.1666

Data Index: 1334511 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.4992. Min Act: -0.1691

Data Index: 1083693 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.4921. Min Act: -0.1666

Data Index: 78776 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.4799. Min Act: -0.1676

Data Index: 130276 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.4585. Min Act: -0.1666

Data Index: 1619779 (Python Code)

Max Activating Token Index: 960