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

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

Neuron 1049 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.5160. Min Act: -0.1700

Data Index: 926224 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.4690. Min Act: -0.1700

Data Index: 949778 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.4533. Min Act: -0.1700

Data Index: 1652394 (Python Code)

Max Activating Token Index: 506

Text #3

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.4062. Min Act: -0.1646

Data Index: 1474069 (Python Code)

Max Activating Token Index: 507

Text #4

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.4376. Min Act: -0.1699

Data Index: 1553660 (Python Code)

Max Activating Token Index: 930

Text #5

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.4219. Min Act: -0.1700

Data Index: 1293922 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.4219. Min Act: -0.1700

Data Index: 454820 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.4062. Min Act: -0.1700

Data Index: 69592 (C4 (Web Text))

Max Activating Token Index: 972

Text #8

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.4219. Min Act: -0.1700

Data Index: 1363196 (Python Code)

Max Activating Token Index: 803

Text #9

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.3906. Min Act: -0.1699

Data Index: 1434893 (Python Code)

Max Activating Token Index: 364

Text #10

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.3592. Min Act: -0.1646

Data Index: 1454449 (Python Code)

Max Activating Token Index: 167

Text #11

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.3749. Min Act: -0.1700

Data Index: 1604954 (Python Code)

Max Activating Token Index: 375

Text #12

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.3435. Min Act: -0.1700

Data Index: 1497437 (Python Code)

Max Activating Token Index: 309

Text #13

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.3435. Min Act: -0.1580

Data Index: 1430444 (Python Code)

Max Activating Token Index: 545

Text #14

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.3749. Min Act: -0.1697

Data Index: 1525750 (Python Code)

Max Activating Token Index: 233

Text #15

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.3592. Min Act: -0.1700

Data Index: 1626099 (Python Code)

Max Activating Token Index: 893

Text #16

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.3435. Min Act: -0.1700

Data Index: 1422973 (Python Code)

Max Activating Token Index: 141

Text #17

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.3435. Min Act: -0.1700

Data Index: 1638826 (Python Code)

Max Activating Token Index: 388

Text #18

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.3121. Min Act: -0.1700

Data Index: 1320358 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.3121. Min Act: -0.1697

Data Index: 1392997 (Python Code)

Max Activating Token Index: 852