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

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

Neuron 1290 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: 3.2524. Min Range: -3.2524

Max Act: 3.2524. Min Act: -0.1700

Data Index: 1541349 (Python Code)

Max Activating Token Index: 863

Text #1

Max Range: 3.2524. Min Range: -3.2524

Max Act: 3.2052. Min Act: -0.1700

Data Index: 51392 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 3.2524. Min Range: -3.2524

Max Act: 3.2052. Min Act: -0.1700

Data Index: 630945 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 3.2524. Min Range: -3.2524

Max Act: 3.1737. Min Act: -0.1700

Data Index: 270934 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 3.2524. Min Range: -3.2524

Max Act: 3.1423. Min Act: -0.1700

Data Index: 1576115 (Python Code)

Max Activating Token Index: 36

Text #5

Max Range: 3.2524. Min Range: -3.2524

Max Act: 3.1107. Min Act: -0.1700

Data Index: 604132 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 3.2524. Min Range: -3.2524

Max Act: 3.0950. Min Act: -0.1700

Data Index: 407186 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 3.2524. Min Range: -3.2524

Max Act: 3.0792. Min Act: -0.1700

Data Index: 213191 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 3.2524. Min Range: -3.2524

Max Act: 3.0950. Min Act: -0.1700

Data Index: 326524 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 3.2524. Min Range: -3.2524

Max Act: 3.0476. Min Act: -0.1700

Data Index: 1046058 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 3.2524. Min Range: -3.2524

Max Act: 3.0634. Min Act: -0.1700

Data Index: 1083039 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 3.2524. Min Range: -3.2524

Max Act: 3.0476. Min Act: -0.1700

Data Index: 898976 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 3.2524. Min Range: -3.2524

Max Act: 3.0476. Min Act: -0.1700

Data Index: 38229 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 3.2524. Min Range: -3.2524

Max Act: 3.0319. Min Act: -0.1700

Data Index: 164721 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 3.2524. Min Range: -3.2524

Max Act: 3.0161. Min Act: -0.1700

Data Index: 269750 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 3.2524. Min Range: -3.2524

Max Act: 3.0476. Min Act: -0.1700

Data Index: 271635 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 3.2524. Min Range: -3.2524

Max Act: 3.0476. Min Act: -0.1700

Data Index: 1337415 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 3.2524. Min Range: -3.2524

Max Act: 3.0634. Min Act: -0.1700

Data Index: 950584 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 3.2524. Min Range: -3.2524

Max Act: 3.0476. Min Act: -0.1700

Data Index: 903862 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 3.2524. Min Range: -3.2524

Max Act: 3.0319. Min Act: -0.1700

Data Index: 856328 (C4 (Web Text))

Max Activating Token Index: 587