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

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

Neuron 1846 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: 3.3038. Min Range: -3.3038

Max Act: 3.3038. Min Act: -0.1700

Data Index: 117496 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 3.3038. Min Range: -3.3038

Max Act: 3.1465. Min Act: -0.1682

Data Index: 534967 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 3.3038. Min Range: -3.3038

Max Act: 3.0835. Min Act: -0.1700

Data Index: 750212 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 3.3038. Min Range: -3.3038

Max Act: 3.0835. Min Act: -0.1700

Data Index: 796859 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 3.3038. Min Range: -3.3038

Max Act: 3.0835. Min Act: -0.1695

Data Index: 1166610 (C4 (Web Text))

Max Activating Token Index: 412

Text #5

Max Range: 3.3038. Min Range: -3.3038

Max Act: 3.0519. Min Act: -0.1700

Data Index: 750510 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 3.3038. Min Range: -3.3038

Max Act: 3.0361. Min Act: -0.1700

Data Index: 903387 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 3.3038. Min Range: -3.3038

Max Act: 3.0519. Min Act: -0.1700

Data Index: 554487 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 3.3038. Min Range: -3.3038

Max Act: 3.0361. Min Act: -0.1700

Data Index: 452059 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.9887. Min Act: -0.1700

Data Index: 1033772 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.9887. Min Act: -0.1700

Data Index: 151606 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.9729. Min Act: -0.1700

Data Index: 1052158 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.9570. Min Act: -0.1694

Data Index: 963980 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.9729. Min Act: -0.1700

Data Index: 703853 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.9729. Min Act: -0.1700

Data Index: 1284199 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.9570. Min Act: -0.1700

Data Index: 853819 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.9570. Min Act: -0.1700

Data Index: 918198 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.9570. Min Act: -0.1700

Data Index: 691985 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.9570. Min Act: -0.1700

Data Index: 835329 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.9570. Min Act: -0.1700

Data Index: 408945 (C4 (Web Text))

Max Activating Token Index: 50