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

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

Neuron 294 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6586. Min Range: -3.6586

Max Act: 3.6586. Min Act: -0.1700

Data Index: 486868 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 3.6586. Min Range: -3.6586

Max Act: 3.6273. Min Act: -0.1699

Data Index: 1225135 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 3.6586. Min Range: -3.6586

Max Act: 3.5960. Min Act: -0.1700

Data Index: 1046487 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 3.6586. Min Range: -3.6586

Max Act: 3.5960. Min Act: -0.1698

Data Index: 669148 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 3.6586. Min Range: -3.6586

Max Act: 3.5334. Min Act: -0.1700

Data Index: 1312406 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 3.6586. Min Range: -3.6586

Max Act: 3.5020. Min Act: -0.1698

Data Index: 444984 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 3.6586. Min Range: -3.6586

Max Act: 3.5020. Min Act: -0.1700

Data Index: 1330594 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 3.6586. Min Range: -3.6586

Max Act: 3.5020. Min Act: -0.1700

Data Index: 873506 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 3.6586. Min Range: -3.6586

Max Act: 3.5020. Min Act: -0.1700

Data Index: 695793 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 3.6586. Min Range: -3.6586

Max Act: 3.5020. Min Act: -0.1699

Data Index: 852798 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 3.6586. Min Range: -3.6586

Max Act: 3.4080. Min Act: -0.1700

Data Index: 192419 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 3.6586. Min Range: -3.6586

Max Act: 3.4707. Min Act: -0.1700

Data Index: 321186 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 3.6586. Min Range: -3.6586

Max Act: 3.5020. Min Act: -0.1700

Data Index: 150987 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 3.6586. Min Range: -3.6586

Max Act: 3.4393. Min Act: -0.1699

Data Index: 95531 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 3.6586. Min Range: -3.6586

Max Act: 3.4707. Min Act: -0.1700

Data Index: 978417 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 3.6586. Min Range: -3.6586

Max Act: 3.4707. Min Act: -0.1700

Data Index: 622996 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 3.6586. Min Range: -3.6586

Max Act: 3.4080. Min Act: -0.1700

Data Index: 1007046 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 3.6586. Min Range: -3.6586

Max Act: 3.4707. Min Act: -0.1700

Data Index: 1163628 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 3.6586. Min Range: -3.6586

Max Act: 3.4707. Min Act: -0.1700

Data Index: 742263 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 3.6586. Min Range: -3.6586

Max Act: 3.4393. Min Act: -0.1700

Data Index: 466180 (C4 (Web Text))

Max Activating Token Index: 884