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

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

Neuron 215 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: 5.0123. Min Range: -5.0123

Max Act: 5.0123. Min Act: -0.1700

Data Index: 476036 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.9342. Min Act: -0.1700

Data Index: 505398 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.9654. Min Act: -0.1700

Data Index: 1459563 (Python Code)

Max Activating Token Index: 897

Text #3

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.9498. Min Act: -0.1700

Data Index: 489184 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.8873. Min Act: -0.1700

Data Index: 199936 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.8795. Min Act: -0.1700

Data Index: 1362948 (Python Code)

Max Activating Token Index: 960

Text #6

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.8561. Min Act: -0.1700

Data Index: 571377 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.9107. Min Act: -0.1700

Data Index: 1124841 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.8170. Min Act: -0.1700

Data Index: 686298 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.7779. Min Act: -0.1700

Data Index: 201687 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.7857. Min Act: -0.1700

Data Index: 1520742 (Python Code)

Max Activating Token Index: 646

Text #11

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.8248. Min Act: -0.1700

Data Index: 907296 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.7857. Min Act: -0.1700

Data Index: 1545838 (Python Code)

Max Activating Token Index: 255

Text #13

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.7701. Min Act: -0.1700

Data Index: 526102 (C4 (Web Text))

Max Activating Token Index: 457

Text #14

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.7936. Min Act: -0.1700

Data Index: 950459 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.7467. Min Act: -0.1700

Data Index: 9732 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.7779. Min Act: -0.1700

Data Index: 400419 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.7623. Min Act: -0.1700

Data Index: 585766 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.7857. Min Act: -0.1700

Data Index: 328295 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.7389. Min Act: -0.1700

Data Index: 1605919 (Python Code)

Max Activating Token Index: 99