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

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

Neuron 1286 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8404. Min Range: -3.8404

Max Act: 3.8404. Min Act: -0.1700

Data Index: 557534 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 3.8404. Min Range: -3.8404

Max Act: 3.7778. Min Act: -0.1700

Data Index: 401606 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 3.8404. Min Range: -3.8404

Max Act: 3.7466. Min Act: -0.1700

Data Index: 353849 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 3.8404. Min Range: -3.8404

Max Act: 3.6840. Min Act: -0.1700

Data Index: 214731 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 3.8404. Min Range: -3.8404

Max Act: 3.6214. Min Act: -0.1700

Data Index: 1116779 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 3.8404. Min Range: -3.8404

Max Act: 3.5900. Min Act: -0.1700

Data Index: 197644 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 3.8404. Min Range: -3.8404

Max Act: 3.5587. Min Act: -0.1700

Data Index: 99764 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 3.8404. Min Range: -3.8404

Max Act: 3.5900. Min Act: -0.1700

Data Index: 615318 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 3.8404. Min Range: -3.8404

Max Act: 3.5587. Min Act: -0.1700

Data Index: 258 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 3.8404. Min Range: -3.8404

Max Act: 3.5587. Min Act: -0.1700

Data Index: 1301161 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 3.8404. Min Range: -3.8404

Max Act: 3.5587. Min Act: -0.1700

Data Index: 335573 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 3.8404. Min Range: -3.8404

Max Act: 3.5587. Min Act: -0.1700

Data Index: 929330 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 3.8404. Min Range: -3.8404

Max Act: 3.5587. Min Act: -0.1700

Data Index: 445785 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 3.8404. Min Range: -3.8404

Max Act: 3.5587. Min Act: -0.1700

Data Index: 844439 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 3.8404. Min Range: -3.8404

Max Act: 3.5274. Min Act: -0.1700

Data Index: 296205 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 3.8404. Min Range: -3.8404

Max Act: 3.5274. Min Act: -0.1700

Data Index: 390078 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 3.8404. Min Range: -3.8404

Max Act: 3.5274. Min Act: -0.1700

Data Index: 69672 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 3.8404. Min Range: -3.8404

Max Act: 3.5274. Min Act: -0.1700

Data Index: 492935 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 3.8404. Min Range: -3.8404

Max Act: 3.5274. Min Act: -0.1700

Data Index: 249105 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 3.8404. Min Range: -3.8404

Max Act: 3.5274. Min Act: -0.1700

Data Index: 994347 (C4 (Web Text))

Max Activating Token Index: 101