Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1420 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.8477. Min Act: -0.1700

Data Index: 842527 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.7539. Min Act: -0.1700

Data Index: 126929 (C4 (Web Text))

Max Activating Token Index: 993

Text #2

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.6600. Min Act: -0.1700

Data Index: 830563 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.6130. Min Act: -0.1700

Data Index: 1090623 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.5504. Min Act: -0.1700

Data Index: 1207059 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.5347. Min Act: -0.1700

Data Index: 1371742 (Python Code)

Max Activating Token Index: 882

Text #6

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.5974. Min Act: -0.1700

Data Index: 140246 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.5034. Min Act: -0.1700

Data Index: 740732 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.5660. Min Act: -0.1700

Data Index: 605509 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.5191. Min Act: -0.1700

Data Index: 927050 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.5191. Min Act: -0.1700

Data Index: 381026 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.5034. Min Act: -0.1700

Data Index: 1186825 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.4877. Min Act: -0.1700

Data Index: 926879 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.4720. Min Act: -0.1700

Data Index: 1247763 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.4720. Min Act: -0.1700

Data Index: 1131090 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.4564. Min Act: -0.1700

Data Index: 1011878 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.4720. Min Act: -0.1700

Data Index: 742322 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.4720. Min Act: -0.1700

Data Index: 694647 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.4250. Min Act: -0.1700

Data Index: 901265 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.4250. Min Act: -0.1700

Data Index: 1400243 (Python Code)

Max Activating Token Index: 912