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

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

Neuron 420 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6740. Min Range: -5.6740

Max Act: 5.6427. Min Act: -0.1700

Data Index: 465552 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 5.6740. Min Range: -5.6740

Max Act: 5.6740. Min Act: -0.1700

Data Index: 777563 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 5.6740. Min Range: -5.6740

Max Act: 5.5490. Min Act: -0.1700

Data Index: 831261 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 5.6740. Min Range: -5.6740

Max Act: 5.4240. Min Act: -0.1700

Data Index: 1327615 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 5.6740. Min Range: -5.6740

Max Act: 5.4240. Min Act: -0.1700

Data Index: 1196699 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 5.6740. Min Range: -5.6740

Max Act: 5.3927. Min Act: -0.1700

Data Index: 914651 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 5.6740. Min Range: -5.6740

Max Act: 5.3927. Min Act: -0.1700

Data Index: 1018411 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 5.6740. Min Range: -5.6740

Max Act: 5.2990. Min Act: -0.1700

Data Index: 647554 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 5.6740. Min Range: -5.6740

Max Act: 5.4240. Min Act: -0.1700

Data Index: 148632 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 5.6740. Min Range: -5.6740

Max Act: 5.2990. Min Act: -0.1700

Data Index: 188963 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 5.6740. Min Range: -5.6740

Max Act: 5.3302. Min Act: -0.1700

Data Index: 1234939 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 5.6740. Min Range: -5.6740

Max Act: 5.3302. Min Act: -0.1700

Data Index: 992136 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 5.6740. Min Range: -5.6740

Max Act: 5.3302. Min Act: -0.1700

Data Index: 864039 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 5.6740. Min Range: -5.6740

Max Act: 5.2990. Min Act: -0.1700

Data Index: 268420 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 5.6740. Min Range: -5.6740

Max Act: 5.2990. Min Act: -0.1699

Data Index: 927420 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 5.6740. Min Range: -5.6740

Max Act: 5.2677. Min Act: -0.1700

Data Index: 1078034 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 5.6740. Min Range: -5.6740

Max Act: 5.2365. Min Act: -0.1700

Data Index: 662585 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 5.6740. Min Range: -5.6740

Max Act: 5.2677. Min Act: -0.1700

Data Index: 844163 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 5.6740. Min Range: -5.6740

Max Act: 5.2052. Min Act: -0.1700

Data Index: 765459 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 5.6740. Min Range: -5.6740

Max Act: 5.2365. Min Act: -0.1700

Data Index: 53866 (C4 (Web Text))

Max Activating Token Index: 600