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

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

Neuron 404 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: 3.6950. Min Range: -3.6950

Max Act: 3.6950. Min Act: -0.1700

Data Index: 305829 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.5071. Min Act: -0.1700

Data Index: 1045006 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.4444. Min Act: -0.1700

Data Index: 1269975 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.4758. Min Act: -0.1700

Data Index: 363871 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.4444. Min Act: -0.1700

Data Index: 994642 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.4758. Min Act: -0.1700

Data Index: 321186 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.4758. Min Act: -0.1700

Data Index: 900191 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.4444. Min Act: -0.1700

Data Index: 863530 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.4444. Min Act: -0.1700

Data Index: 718362 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.4444. Min Act: -0.1700

Data Index: 1192630 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.4131. Min Act: -0.1700

Data Index: 387610 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.4131. Min Act: -0.1700

Data Index: 563092 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.4444. Min Act: -0.1700

Data Index: 1096940 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.4444. Min Act: -0.1700

Data Index: 6325 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.4758. Min Act: -0.1700

Data Index: 157288 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.4131. Min Act: -0.1700

Data Index: 895595 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.3817. Min Act: -0.1700

Data Index: 876010 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.4131. Min Act: -0.1700

Data Index: 578208 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.4131. Min Act: -0.1700

Data Index: 437174 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.4444. Min Act: -0.1700

Data Index: 578017 (C4 (Web Text))

Max Activating Token Index: 862