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

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

Neuron 925 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: 3.8511. Min Range: -3.8511

Max Act: 3.8511. Min Act: -0.1700

Data Index: 1302388 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.6633. Min Act: -0.1699

Data Index: 522075 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.4597. Min Act: -0.1700

Data Index: 1469756 (Python Code)

Max Activating Token Index: 514

Text #3

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.4754. Min Act: -0.1700

Data Index: 989893 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.4754. Min Act: -0.1700

Data Index: 607455 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.4754. Min Act: -0.1700

Data Index: 1429195 (Python Code)

Max Activating Token Index: 108

Text #6

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.4127. Min Act: -0.1700

Data Index: 1521648 (Python Code)

Max Activating Token Index: 817

Text #7

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.4127. Min Act: -0.1700

Data Index: 182997 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.4441. Min Act: -0.1700

Data Index: 1634161 (Python Code)

Max Activating Token Index: 264

Text #9

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.4127. Min Act: -0.1700

Data Index: 1643188 (Python Code)

Max Activating Token Index: 37

Text #10

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.4284. Min Act: -0.1700

Data Index: 1086469 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.4284. Min Act: -0.1700

Data Index: 183589 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.3813. Min Act: -0.1700

Data Index: 1360465 (Python Code)

Max Activating Token Index: 35

Text #13

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.4127. Min Act: -0.1700

Data Index: 872908 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.4284. Min Act: -0.1700

Data Index: 73733 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.3970. Min Act: -0.1700

Data Index: 782342 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.3813. Min Act: -0.1700

Data Index: 1615643 (Python Code)

Max Activating Token Index: 32

Text #17

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.4127. Min Act: -0.1700

Data Index: 214937 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.3970. Min Act: -0.1700

Data Index: 440003 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.3970. Min Act: -0.1700

Data Index: 1554233 (Python Code)

Max Activating Token Index: 34