Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1349 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.7559. Min Range: -3.7559

Max Act: 3.7559. Min Act: -0.1700

Data Index: 1358393 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 3.7559. Min Range: -3.7559

Max Act: 3.5367. Min Act: -0.1700

Data Index: 268452 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 3.7559. Min Range: -3.7559

Max Act: 3.4897. Min Act: -0.1700

Data Index: 1169408 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 3.7559. Min Range: -3.7559

Max Act: 3.4741. Min Act: -0.1700

Data Index: 317734 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 3.7559. Min Range: -3.7559

Max Act: 3.4584. Min Act: -0.1700

Data Index: 684103 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 3.7559. Min Range: -3.7559

Max Act: 3.4741. Min Act: -0.1700

Data Index: 657334 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 3.7559. Min Range: -3.7559

Max Act: 3.4427. Min Act: -0.1700

Data Index: 1262058 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 3.7559. Min Range: -3.7559

Max Act: 3.4427. Min Act: -0.1700

Data Index: 904347 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 3.7559. Min Range: -3.7559

Max Act: 3.4270. Min Act: -0.1700

Data Index: 582623 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 3.7559. Min Range: -3.7559

Max Act: 3.4427. Min Act: -0.1700

Data Index: 310094 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 3.7559. Min Range: -3.7559

Max Act: 3.4270. Min Act: -0.1700

Data Index: 1357541 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 3.7559. Min Range: -3.7559

Max Act: 3.4270. Min Act: -0.1700

Data Index: 1457606 (Python Code)

Max Activating Token Index: 9

Text #12

Max Range: 3.7559. Min Range: -3.7559

Max Act: 3.4113. Min Act: -0.1700

Data Index: 131396 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 3.7559. Min Range: -3.7559

Max Act: 3.3800. Min Act: -0.1700

Data Index: 1253825 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 3.7559. Min Range: -3.7559

Max Act: 3.3800. Min Act: -0.1700

Data Index: 942468 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 3.7559. Min Range: -3.7559

Max Act: 3.3957. Min Act: -0.1700

Data Index: 537193 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 3.7559. Min Range: -3.7559

Max Act: 3.3486. Min Act: -0.1700

Data Index: 567765 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 3.7559. Min Range: -3.7559

Max Act: 3.3957. Min Act: -0.1700

Data Index: 1296528 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 3.7559. Min Range: -3.7559

Max Act: 3.3486. Min Act: -0.1700

Data Index: 826161 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 3.7559. Min Range: -3.7559

Max Act: 3.3643. Min Act: -0.1700

Data Index: 119204 (C4 (Web Text))

Max Activating Token Index: 33