Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1218 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.7885. Min Act: -0.1700

Data Index: 1455041 (Python Code)

Max Activating Token Index: 37

Text #1

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.8041. Min Act: -0.1700

Data Index: 1439956 (Python Code)

Max Activating Token Index: 16

Text #2

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.7885. Min Act: -0.1700

Data Index: 1433777 (Python Code)

Max Activating Token Index: 33

Text #3

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.7729. Min Act: -0.1700

Data Index: 384610 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.7729. Min Act: -0.1700

Data Index: 1407507 (Python Code)

Max Activating Token Index: 613

Text #5

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.7729. Min Act: -0.1700

Data Index: 1520266 (Python Code)

Max Activating Token Index: 623

Text #6

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.7885. Min Act: -0.1700

Data Index: 1456825 (Python Code)

Max Activating Token Index: 973

Text #7

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.7572. Min Act: -0.1700

Data Index: 1433342 (Python Code)

Max Activating Token Index: 476

Text #8

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.7572. Min Act: -0.1700

Data Index: 1483073 (Python Code)

Max Activating Token Index: 630

Text #9

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.7416. Min Act: -0.1700

Data Index: 1611996 (Python Code)

Max Activating Token Index: 219

Text #10

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.7572. Min Act: -0.1700

Data Index: 1461774 (Python Code)

Max Activating Token Index: 604

Text #11

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.7416. Min Act: -0.1700

Data Index: 1555678 (Python Code)

Max Activating Token Index: 538

Text #12

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.7259. Min Act: -0.1700

Data Index: 1603847 (Python Code)

Max Activating Token Index: 914

Text #13

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.7416. Min Act: -0.1700

Data Index: 1484646 (Python Code)

Max Activating Token Index: 223

Text #14

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.7416. Min Act: -0.1700

Data Index: 1378305 (Python Code)

Max Activating Token Index: 167

Text #15

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.7416. Min Act: -0.1700

Data Index: 1473050 (Python Code)

Max Activating Token Index: 928

Text #16

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.7103. Min Act: -0.1700

Data Index: 1577197 (Python Code)

Max Activating Token Index: 970

Text #17

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.6946. Min Act: -0.1700

Data Index: 1383150 (Python Code)

Max Activating Token Index: 950

Text #18

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.7103. Min Act: -0.1700

Data Index: 1520195 (Python Code)

Max Activating Token Index: 761

Text #19

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.7103. Min Act: -0.1700

Data Index: 1467997 (Python Code)

Max Activating Token Index: 455