Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 69 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.1975. Min Range: -5.1975

Max Act: 5.1975. Min Act: -0.1700

Data Index: 767004 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 5.1975. Min Range: -5.1975

Max Act: 5.0725. Min Act: -0.1700

Data Index: 1341347 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 5.1975. Min Range: -5.1975

Max Act: 5.0413. Min Act: -0.1700

Data Index: 979564 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 5.1975. Min Range: -5.1975

Max Act: 5.0100. Min Act: -0.1700

Data Index: 913176 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 5.1975. Min Range: -5.1975

Max Act: 4.9475. Min Act: -0.1700

Data Index: 1341089 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 5.1975. Min Range: -5.1975

Max Act: 4.9788. Min Act: -0.1700

Data Index: 1053298 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 5.1975. Min Range: -5.1975

Max Act: 4.9475. Min Act: -0.1700

Data Index: 114068 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 5.1975. Min Range: -5.1975

Max Act: 4.8850. Min Act: -0.1700

Data Index: 480998 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 5.1975. Min Range: -5.1975

Max Act: 4.8850. Min Act: -0.1700

Data Index: 451915 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 5.1975. Min Range: -5.1975

Max Act: 4.8850. Min Act: -0.1700

Data Index: 954917 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 5.1975. Min Range: -5.1975

Max Act: 4.8225. Min Act: -0.1700

Data Index: 376195 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 5.1975. Min Range: -5.1975

Max Act: 4.8225. Min Act: -0.1700

Data Index: 105581 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 5.1975. Min Range: -5.1975

Max Act: 4.7913. Min Act: -0.1700

Data Index: 901421 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 5.1975. Min Range: -5.1975

Max Act: 4.7600. Min Act: -0.1700

Data Index: 778072 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 5.1975. Min Range: -5.1975

Max Act: 4.8225. Min Act: -0.1700

Data Index: 1313192 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 5.1975. Min Range: -5.1975

Max Act: 4.7913. Min Act: -0.1700

Data Index: 203363 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 5.1975. Min Range: -5.1975

Max Act: 4.7600. Min Act: -0.1700

Data Index: 527032 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 5.1975. Min Range: -5.1975

Max Act: 4.7913. Min Act: -0.1700

Data Index: 335185 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 5.1975. Min Range: -5.1975

Max Act: 4.7913. Min Act: -0.1700

Data Index: 372465 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 5.1975. Min Range: -5.1975

Max Act: 4.7600. Min Act: -0.1700

Data Index: 1083281 (C4 (Web Text))

Max Activating Token Index: 4