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

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

Neuron 1985 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.1594. Min Range: -3.1594

Max Act: 3.1594. Min Act: -0.1700

Data Index: 378263 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 3.1594. Min Range: -3.1594

Max Act: 3.1436. Min Act: -0.1700

Data Index: 259131 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 3.1594. Min Range: -3.1594

Max Act: 3.1594. Min Act: -0.1700

Data Index: 1230206 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 3.1594. Min Range: -3.1594

Max Act: 3.1436. Min Act: -0.1700

Data Index: 959356 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 3.1594. Min Range: -3.1594

Max Act: 3.1279. Min Act: -0.1700

Data Index: 239518 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 3.1594. Min Range: -3.1594

Max Act: 3.1121. Min Act: -0.1700

Data Index: 1031636 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 3.1594. Min Range: -3.1594

Max Act: 3.0806. Min Act: -0.1700

Data Index: 72894 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 3.1594. Min Range: -3.1594

Max Act: 3.0806. Min Act: -0.1700

Data Index: 618990 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 3.1594. Min Range: -3.1594

Max Act: 3.0490. Min Act: -0.1700

Data Index: 1210987 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 3.1594. Min Range: -3.1594

Max Act: 3.0332. Min Act: -0.1700

Data Index: 1078636 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 3.1594. Min Range: -3.1594

Max Act: 3.0174. Min Act: -0.1700

Data Index: 476922 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 3.1594. Min Range: -3.1594

Max Act: 3.0016. Min Act: -0.1700

Data Index: 161235 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 3.1594. Min Range: -3.1594

Max Act: 3.0332. Min Act: -0.1700

Data Index: 538463 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 3.1594. Min Range: -3.1594

Max Act: 3.0016. Min Act: -0.1700

Data Index: 443087 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 3.1594. Min Range: -3.1594

Max Act: 3.0174. Min Act: -0.1700

Data Index: 434363 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 3.1594. Min Range: -3.1594

Max Act: 3.0016. Min Act: -0.1700

Data Index: 302650 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 3.1594. Min Range: -3.1594

Max Act: 3.0016. Min Act: -0.1700

Data Index: 1227503 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 3.1594. Min Range: -3.1594

Max Act: 2.9858. Min Act: -0.1700

Data Index: 546692 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 3.1594. Min Range: -3.1594

Max Act: 3.0016. Min Act: -0.1700

Data Index: 50094 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 3.1594. Min Range: -3.1594

Max Act: 2.9542. Min Act: -0.1700

Data Index: 1160400 (C4 (Web Text))

Max Activating Token Index: 940