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

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

Neuron 466 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: 3.5805. Min Range: -3.5805

Max Act: 3.5805. Min Act: -0.1700

Data Index: 805190 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 3.5805. Min Range: -3.5805

Max Act: 3.5805. Min Act: -0.1700

Data Index: 1326580 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 3.5805. Min Range: -3.5805

Max Act: 3.4865. Min Act: -0.1700

Data Index: 1120211 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 3.5805. Min Range: -3.5805

Max Act: 3.4865. Min Act: -0.1700

Data Index: 611489 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 3.5805. Min Range: -3.5805

Max Act: 3.3924. Min Act: -0.1700

Data Index: 1193521 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 3.5805. Min Range: -3.5805

Max Act: 3.3924. Min Act: -0.1700

Data Index: 1079115 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 3.5805. Min Range: -3.5805

Max Act: 3.4238. Min Act: -0.1700

Data Index: 583383 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 3.5805. Min Range: -3.5805

Max Act: 3.3924. Min Act: -0.1700

Data Index: 256449 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 3.5805. Min Range: -3.5805

Max Act: 3.3924. Min Act: -0.1700

Data Index: 167829 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 3.5805. Min Range: -3.5805

Max Act: 3.4238. Min Act: -0.1700

Data Index: 302840 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 3.5805. Min Range: -3.5805

Max Act: 3.4238. Min Act: -0.1700

Data Index: 1319506 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 3.5805. Min Range: -3.5805

Max Act: 3.3924. Min Act: -0.1700

Data Index: 447486 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 3.5805. Min Range: -3.5805

Max Act: 3.3611. Min Act: -0.1700

Data Index: 1239651 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 3.5805. Min Range: -3.5805

Max Act: 3.3611. Min Act: -0.1700

Data Index: 970366 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 3.5805. Min Range: -3.5805

Max Act: 3.3924. Min Act: -0.1700

Data Index: 801230 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 3.5805. Min Range: -3.5805

Max Act: 3.3611. Min Act: -0.1700

Data Index: 160452 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 3.5805. Min Range: -3.5805

Max Act: 3.3611. Min Act: -0.1700

Data Index: 1076920 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 3.5805. Min Range: -3.5805

Max Act: 3.3611. Min Act: -0.1700

Data Index: 68947 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 3.5805. Min Range: -3.5805

Max Act: 3.2983. Min Act: -0.1700

Data Index: 10803 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 3.5805. Min Range: -3.5805

Max Act: 3.3611. Min Act: -0.1700

Data Index: 1119677 (C4 (Web Text))

Max Activating Token Index: 309