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

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

Neuron 823 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5575. Min Range: -3.5575

Max Act: 3.5418. Min Act: -0.1700

Data Index: 348742 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 3.5575. Min Range: -3.5575

Max Act: 3.5575. Min Act: -0.1700

Data Index: 1200350 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 3.5575. Min Range: -3.5575

Max Act: 3.4948. Min Act: -0.1700

Data Index: 488541 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 3.5575. Min Range: -3.5575

Max Act: 3.4635. Min Act: -0.1700

Data Index: 478953 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 3.5575. Min Range: -3.5575

Max Act: 3.4792. Min Act: -0.1700

Data Index: 872592 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 3.5575. Min Range: -3.5575

Max Act: 3.4478. Min Act: -0.1700

Data Index: 983051 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 3.5575. Min Range: -3.5575

Max Act: 3.3851. Min Act: -0.1700

Data Index: 1210981 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 3.5575. Min Range: -3.5575

Max Act: 3.3851. Min Act: -0.1700

Data Index: 876021 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 3.5575. Min Range: -3.5575

Max Act: 3.3851. Min Act: -0.1700

Data Index: 403812 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 3.5575. Min Range: -3.5575

Max Act: 3.3694. Min Act: -0.1700

Data Index: 597139 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 3.5575. Min Range: -3.5575

Max Act: 3.3537. Min Act: -0.1700

Data Index: 379190 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 3.5575. Min Range: -3.5575

Max Act: 3.3537. Min Act: -0.1700

Data Index: 546366 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 3.5575. Min Range: -3.5575

Max Act: 3.3223. Min Act: -0.1700

Data Index: 243166 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 3.5575. Min Range: -3.5575

Max Act: 3.3380. Min Act: -0.1700

Data Index: 130055 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 3.5575. Min Range: -3.5575

Max Act: 3.3066. Min Act: -0.1700

Data Index: 756188 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 3.5575. Min Range: -3.5575

Max Act: 3.3223. Min Act: -0.1700

Data Index: 812554 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 3.5575. Min Range: -3.5575

Max Act: 3.3223. Min Act: -0.1700

Data Index: 1349405 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 3.5575. Min Range: -3.5575

Max Act: 3.2909. Min Act: -0.1700

Data Index: 1234776 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 3.5575. Min Range: -3.5575

Max Act: 3.3223. Min Act: -0.1700

Data Index: 835904 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 3.5575. Min Range: -3.5575

Max Act: 3.2909. Min Act: -0.1700

Data Index: 451313 (C4 (Web Text))

Max Activating Token Index: 679