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

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

Neuron 1270 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9406. Min Range: -5.9406

Max Act: 5.9406. Min Act: -0.1700

Data Index: 717892 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 5.9406. Min Range: -5.9406

Max Act: 5.5656. Min Act: -0.1700

Data Index: 316537 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 5.9406. Min Range: -5.9406

Max Act: 5.5031. Min Act: -0.1700

Data Index: 417182 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 5.9406. Min Range: -5.9406

Max Act: 5.4719. Min Act: -0.1700

Data Index: 693916 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 5.9406. Min Range: -5.9406

Max Act: 5.4094. Min Act: -0.1700

Data Index: 1076404 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 5.9406. Min Range: -5.9406

Max Act: 5.5031. Min Act: -0.1700

Data Index: 334535 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 5.9406. Min Range: -5.9406

Max Act: 5.4094. Min Act: -0.1700

Data Index: 299317 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 5.9406. Min Range: -5.9406

Max Act: 5.4406. Min Act: -0.1700

Data Index: 128720 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 5.9406. Min Range: -5.9406

Max Act: 5.4094. Min Act: -0.1699

Data Index: 1217891 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 5.9406. Min Range: -5.9406

Max Act: 5.3469. Min Act: -0.1700

Data Index: 686989 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 5.9406. Min Range: -5.9406

Max Act: 5.2844. Min Act: -0.1700

Data Index: 89164 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 5.9406. Min Range: -5.9406

Max Act: 5.3156. Min Act: -0.1700

Data Index: 186288 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 5.9406. Min Range: -5.9406

Max Act: 5.1906. Min Act: -0.1700

Data Index: 672773 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 5.9406. Min Range: -5.9406

Max Act: 5.2844. Min Act: -0.1700

Data Index: 485963 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 5.9406. Min Range: -5.9406

Max Act: 5.2531. Min Act: -0.1700

Data Index: 1213151 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 5.9406. Min Range: -5.9406

Max Act: 5.2844. Min Act: -0.1700

Data Index: 523176 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 5.9406. Min Range: -5.9406

Max Act: 5.1906. Min Act: -0.1700

Data Index: 503752 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 5.9406. Min Range: -5.9406

Max Act: 5.2219. Min Act: -0.1700

Data Index: 768969 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 5.9406. Min Range: -5.9406

Max Act: 5.1906. Min Act: -0.1700

Data Index: 459304 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 5.9406. Min Range: -5.9406

Max Act: 5.1906. Min Act: -0.1700

Data Index: 1097864 (C4 (Web Text))

Max Activating Token Index: 870