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

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

Neuron 1639 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: 3.4324. Min Range: -3.4324

Max Act: 3.4010. Min Act: -0.1700

Data Index: 1336925 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.4324. Min Act: -0.1700

Data Index: 791539 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.4167. Min Act: -0.1700

Data Index: 196723 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.4010. Min Act: -0.1700

Data Index: 434954 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.4324. Min Act: -0.1700

Data Index: 151801 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.3383. Min Act: -0.1700

Data Index: 662501 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.3697. Min Act: -0.1700

Data Index: 502909 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.3540. Min Act: -0.1700

Data Index: 1060047 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.3853. Min Act: -0.1700

Data Index: 641544 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.3540. Min Act: -0.1700

Data Index: 530329 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.3069. Min Act: -0.1700

Data Index: 1096070 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.3383. Min Act: -0.1700

Data Index: 480378 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.2912. Min Act: -0.1700

Data Index: 531683 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.3226. Min Act: -0.1700

Data Index: 669621 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.2754. Min Act: -0.1700

Data Index: 729205 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.2912. Min Act: -0.1700

Data Index: 14579 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.3226. Min Act: -0.1700

Data Index: 809473 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.4010. Min Act: -0.1700

Data Index: 423903 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.2912. Min Act: -0.1700

Data Index: 506256 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.3226. Min Act: -0.1700

Data Index: 650468 (C4 (Web Text))

Max Activating Token Index: 705