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

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

Neuron 1095 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: 3.4874. Min Range: -3.4874

Max Act: 3.4874. Min Act: -0.1700

Data Index: 323248 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.4717. Min Act: -0.1700

Data Index: 1324653 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.4404. Min Act: -0.1700

Data Index: 568688 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.4247. Min Act: -0.1700

Data Index: 1127704 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.4090. Min Act: -0.1700

Data Index: 312644 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.4090. Min Act: -0.1700

Data Index: 440516 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.3933. Min Act: -0.1700

Data Index: 1016857 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.3776. Min Act: -0.1700

Data Index: 1335422 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.4404. Min Act: -0.1700

Data Index: 1271582 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.3776. Min Act: -0.1700

Data Index: 1288227 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.4090. Min Act: -0.1700

Data Index: 894518 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.4090. Min Act: -0.1700

Data Index: 1073019 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.4090. Min Act: -0.1700

Data Index: 1061513 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.4247. Min Act: -0.1700

Data Index: 824087 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.3776. Min Act: -0.1700

Data Index: 995929 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.3933. Min Act: -0.1700

Data Index: 1274990 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.3463. Min Act: -0.1700

Data Index: 55149 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.3619. Min Act: -0.1700

Data Index: 104726 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.3463. Min Act: -0.1700

Data Index: 1043483 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.3619. Min Act: -0.1700

Data Index: 962290 (C4 (Web Text))

Max Activating Token Index: 442