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

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

Neuron 914 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6167. Min Range: -5.6167

Max Act: 5.6167. Min Act: -0.1700

Data Index: 884045 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 5.6167. Min Range: -5.6167

Max Act: 5.4292. Min Act: -0.1700

Data Index: 829475 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 5.6167. Min Range: -5.6167

Max Act: 5.3355. Min Act: -0.1700

Data Index: 144662 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 5.6167. Min Range: -5.6167

Max Act: 5.3667. Min Act: -0.1700

Data Index: 466110 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 5.6167. Min Range: -5.6167

Max Act: 5.3355. Min Act: -0.1700

Data Index: 708668 (C4 (Web Text))

Max Activating Token Index: 605

Text #5

Max Range: 5.6167. Min Range: -5.6167

Max Act: 5.2730. Min Act: -0.1700

Data Index: 1128241 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 5.6167. Min Range: -5.6167

Max Act: 5.2417. Min Act: -0.1700

Data Index: 851559 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 5.6167. Min Range: -5.6167

Max Act: 5.2417. Min Act: -0.1700

Data Index: 409989 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 5.6167. Min Range: -5.6167

Max Act: 5.1792. Min Act: -0.1700

Data Index: 789670 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 5.6167. Min Range: -5.6167

Max Act: 5.1480. Min Act: -0.1700

Data Index: 731721 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 5.6167. Min Range: -5.6167

Max Act: 5.1792. Min Act: -0.1700

Data Index: 712825 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 5.6167. Min Range: -5.6167

Max Act: 5.1480. Min Act: -0.1700

Data Index: 521849 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 5.6167. Min Range: -5.6167

Max Act: 5.1792. Min Act: -0.1700

Data Index: 1012718 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 5.6167. Min Range: -5.6167

Max Act: 5.1167. Min Act: -0.1700

Data Index: 204119 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 5.6167. Min Range: -5.6167

Max Act: 5.0230. Min Act: -0.1700

Data Index: 205817 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 5.6167. Min Range: -5.6167

Max Act: 5.0855. Min Act: -0.1700

Data Index: 421284 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 5.6167. Min Range: -5.6167

Max Act: 5.1792. Min Act: -0.1700

Data Index: 372343 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 5.6167. Min Range: -5.6167

Max Act: 5.0855. Min Act: -0.1700

Data Index: 239751 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 5.6167. Min Range: -5.6167

Max Act: 5.1167. Min Act: -0.1700

Data Index: 192639 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 5.6167. Min Range: -5.6167

Max Act: 5.0542. Min Act: -0.1700

Data Index: 901979 (C4 (Web Text))

Max Activating Token Index: 993