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

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

Neuron 1474 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: 6.1051. Min Range: -6.1051

Max Act: 6.1051. Min Act: -0.1700

Data Index: 1366688 (Python Code)

Max Activating Token Index: 53

Text #1

Max Range: 6.1051. Min Range: -6.1051

Max Act: 6.0426. Min Act: -0.1700

Data Index: 1561058 (Python Code)

Max Activating Token Index: 971

Text #2

Max Range: 6.1051. Min Range: -6.1051

Max Act: 6.0113. Min Act: -0.1700

Data Index: 816240 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 6.1051. Min Range: -6.1051

Max Act: 5.9488. Min Act: -0.1700

Data Index: 1642202 (Python Code)

Max Activating Token Index: 974

Text #4

Max Range: 6.1051. Min Range: -6.1051

Max Act: 5.9176. Min Act: -0.1700

Data Index: 692299 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 6.1051. Min Range: -6.1051

Max Act: 5.9488. Min Act: -0.1700

Data Index: 1437906 (Python Code)

Max Activating Token Index: 74

Text #6

Max Range: 6.1051. Min Range: -6.1051

Max Act: 5.9176. Min Act: -0.1700

Data Index: 1610361 (Python Code)

Max Activating Token Index: 716

Text #7

Max Range: 6.1051. Min Range: -6.1051

Max Act: 5.9488. Min Act: -0.1700

Data Index: 1363374 (Python Code)

Max Activating Token Index: 922

Text #8

Max Range: 6.1051. Min Range: -6.1051

Max Act: 5.8551. Min Act: -0.1700

Data Index: 1430712 (Python Code)

Max Activating Token Index: 124

Text #9

Max Range: 6.1051. Min Range: -6.1051

Max Act: 5.8551. Min Act: -0.1700

Data Index: 1416129 (Python Code)

Max Activating Token Index: 520

Text #10

Max Range: 6.1051. Min Range: -6.1051

Max Act: 5.8551. Min Act: -0.1700

Data Index: 1242661 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 6.1051. Min Range: -6.1051

Max Act: 5.8551. Min Act: -0.1700

Data Index: 1371748 (Python Code)

Max Activating Token Index: 443

Text #12

Max Range: 6.1051. Min Range: -6.1051

Max Act: 5.8863. Min Act: -0.1700

Data Index: 1421969 (Python Code)

Max Activating Token Index: 758

Text #13

Max Range: 6.1051. Min Range: -6.1051

Max Act: 5.8551. Min Act: -0.1700

Data Index: 1437695 (Python Code)

Max Activating Token Index: 59

Text #14

Max Range: 6.1051. Min Range: -6.1051

Max Act: 5.8238. Min Act: -0.1700

Data Index: 1526914 (Python Code)

Max Activating Token Index: 44

Text #15

Max Range: 6.1051. Min Range: -6.1051

Max Act: 5.8551. Min Act: -0.1700

Data Index: 1575425 (Python Code)

Max Activating Token Index: 951

Text #16

Max Range: 6.1051. Min Range: -6.1051

Max Act: 5.8551. Min Act: -0.1700

Data Index: 941379 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 6.1051. Min Range: -6.1051

Max Act: 5.8238. Min Act: -0.1700

Data Index: 146218 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 6.1051. Min Range: -6.1051

Max Act: 5.8238. Min Act: -0.1700

Data Index: 332430 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 6.1051. Min Range: -6.1051

Max Act: 5.7926. Min Act: -0.1700

Data Index: 222784 (C4 (Web Text))

Max Activating Token Index: 607