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

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

Neuron 1548 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5668. Min Range: -3.5668

Max Act: 3.5668. Min Act: -0.1700

Data Index: 919107 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 3.5668. Min Range: -3.5668

Max Act: 3.5355. Min Act: -0.1700

Data Index: 1146616 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 3.5668. Min Range: -3.5668

Max Act: 3.5041. Min Act: -0.1700

Data Index: 383058 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 3.5668. Min Range: -3.5668

Max Act: 3.5041. Min Act: -0.1700

Data Index: 975844 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 3.5668. Min Range: -3.5668

Max Act: 3.4728. Min Act: -0.1700

Data Index: 754854 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 3.5668. Min Range: -3.5668

Max Act: 3.4414. Min Act: -0.1700

Data Index: 178825 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 3.5668. Min Range: -3.5668

Max Act: 3.4101. Min Act: -0.1700

Data Index: 939016 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 3.5668. Min Range: -3.5668

Max Act: 3.3787. Min Act: -0.1700

Data Index: 1003145 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 3.5668. Min Range: -3.5668

Max Act: 3.4414. Min Act: -0.1700

Data Index: 949677 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 3.5668. Min Range: -3.5668

Max Act: 3.3787. Min Act: -0.1700

Data Index: 261675 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 3.5668. Min Range: -3.5668

Max Act: 3.4101. Min Act: -0.1700

Data Index: 65545 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 3.5668. Min Range: -3.5668

Max Act: 3.3473. Min Act: -0.1700

Data Index: 122473 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 3.5668. Min Range: -3.5668

Max Act: 3.3787. Min Act: -0.1700

Data Index: 431804 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 3.5668. Min Range: -3.5668

Max Act: 3.4101. Min Act: -0.1700

Data Index: 359585 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 3.5668. Min Range: -3.5668

Max Act: 3.3473. Min Act: -0.1700

Data Index: 1071226 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 3.5668. Min Range: -3.5668

Max Act: 3.2845. Min Act: -0.1700

Data Index: 896645 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 3.5668. Min Range: -3.5668

Max Act: 3.3473. Min Act: -0.1700

Data Index: 404083 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 3.5668. Min Range: -3.5668

Max Act: 3.3473. Min Act: -0.1700

Data Index: 296110 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 3.5668. Min Range: -3.5668

Max Act: 3.3787. Min Act: -0.1700

Data Index: 1014220 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 3.5668. Min Range: -3.5668

Max Act: 3.4101. Min Act: -0.1700

Data Index: 1105700 (C4 (Web Text))

Max Activating Token Index: 571