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

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

Neuron 1931 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: 5.4403. Min Range: -5.4403

Max Act: 5.4403. Min Act: -0.1700

Data Index: 617034 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 5.4403. Min Range: -5.4403

Max Act: 5.3466. Min Act: -0.1700

Data Index: 1168026 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 5.4403. Min Range: -5.4403

Max Act: 5.3778. Min Act: -0.1700

Data Index: 430047 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 5.4403. Min Range: -5.4403

Max Act: 5.2216. Min Act: -0.1700

Data Index: 778273 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 5.4403. Min Range: -5.4403

Max Act: 5.2216. Min Act: -0.1700

Data Index: 1265087 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 5.4403. Min Range: -5.4403

Max Act: 5.2216. Min Act: -0.1700

Data Index: 958244 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 5.4403. Min Range: -5.4403

Max Act: 5.2216. Min Act: -0.1700

Data Index: 83289 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 5.4403. Min Range: -5.4403

Max Act: 5.2528. Min Act: -0.1699

Data Index: 429445 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 5.4403. Min Range: -5.4403

Max Act: 5.1591. Min Act: -0.1700

Data Index: 378825 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 5.4403. Min Range: -5.4403

Max Act: 5.1591. Min Act: -0.1700

Data Index: 496260 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 5.4403. Min Range: -5.4403

Max Act: 5.1591. Min Act: -0.1695

Data Index: 741747 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 5.4403. Min Range: -5.4403

Max Act: 5.1278. Min Act: -0.1700

Data Index: 205840 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 5.4403. Min Range: -5.4403

Max Act: 5.0966. Min Act: -0.1700

Data Index: 770348 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 5.4403. Min Range: -5.4403

Max Act: 5.0966. Min Act: -0.1700

Data Index: 417647 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 5.4403. Min Range: -5.4403

Max Act: 5.0966. Min Act: -0.1700

Data Index: 352505 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 5.4403. Min Range: -5.4403

Max Act: 5.1278. Min Act: -0.1692

Data Index: 101405 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 5.4403. Min Range: -5.4403

Max Act: 5.0966. Min Act: -0.1700

Data Index: 669787 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 5.4403. Min Range: -5.4403

Max Act: 5.0966. Min Act: -0.1700

Data Index: 740770 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 5.4403. Min Range: -5.4403

Max Act: 5.0966. Min Act: -0.1700

Data Index: 1062193 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 5.4403. Min Range: -5.4403

Max Act: 5.0966. Min Act: -0.1700

Data Index: 1088783 (C4 (Web Text))

Max Activating Token Index: 591