Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 627 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.4480. Min Range: -5.4480

Max Act: 5.4480. Min Act: -0.1700

Data Index: 410662 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 5.4480. Min Range: -5.4480

Max Act: 5.4167. Min Act: -0.1700

Data Index: 858557 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 5.4480. Min Range: -5.4480

Max Act: 5.3542. Min Act: -0.1700

Data Index: 848670 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 5.4480. Min Range: -5.4480

Max Act: 5.3855. Min Act: -0.1700

Data Index: 1010247 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 5.4480. Min Range: -5.4480

Max Act: 5.3230. Min Act: -0.1700

Data Index: 349302 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 5.4480. Min Range: -5.4480

Max Act: 5.3230. Min Act: -0.1700

Data Index: 700968 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 5.4480. Min Range: -5.4480

Max Act: 5.3542. Min Act: -0.1700

Data Index: 655196 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 5.4480. Min Range: -5.4480

Max Act: 5.2605. Min Act: -0.1700

Data Index: 1209079 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 5.4480. Min Range: -5.4480

Max Act: 5.2292. Min Act: -0.1700

Data Index: 11425 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 5.4480. Min Range: -5.4480

Max Act: 5.1980. Min Act: -0.1700

Data Index: 873748 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 5.4480. Min Range: -5.4480

Max Act: 5.2605. Min Act: -0.1700

Data Index: 222942 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 5.4480. Min Range: -5.4480

Max Act: 5.2605. Min Act: -0.1700

Data Index: 791878 (C4 (Web Text))

Max Activating Token Index: 695

Text #12

Max Range: 5.4480. Min Range: -5.4480

Max Act: 5.2917. Min Act: -0.1700

Data Index: 61096 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 5.4480. Min Range: -5.4480

Max Act: 5.2292. Min Act: -0.1700

Data Index: 421316 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 5.4480. Min Range: -5.4480

Max Act: 5.2917. Min Act: -0.1700

Data Index: 1349950 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 5.4480. Min Range: -5.4480

Max Act: 5.2292. Min Act: -0.1700

Data Index: 131054 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 5.4480. Min Range: -5.4480

Max Act: 5.2292. Min Act: -0.1700

Data Index: 617138 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 5.4480. Min Range: -5.4480

Max Act: 5.1980. Min Act: -0.1700

Data Index: 1135093 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 5.4480. Min Range: -5.4480

Max Act: 5.2292. Min Act: -0.1700

Data Index: 533013 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 5.4480. Min Range: -5.4480

Max Act: 5.2292. Min Act: -0.1700

Data Index: 871070 (C4 (Web Text))

Max Activating Token Index: 529