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

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

Neuron 1724 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.9618. Min Act: -0.1700

Data Index: 1043319 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.7743. Min Act: -0.1700

Data Index: 510303 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.7743. Min Act: -0.1700

Data Index: 429265 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.6806. Min Act: -0.1700

Data Index: 1311803 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.6493. Min Act: -0.1700

Data Index: 578612 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.5243. Min Act: -0.1700

Data Index: 758006 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.5556. Min Act: -0.1700

Data Index: 184673 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.5243. Min Act: -0.1700

Data Index: 1324691 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.3993. Min Act: -0.1700

Data Index: 824300 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.4306. Min Act: -0.1700

Data Index: 15494 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.3681. Min Act: -0.1700

Data Index: 386169 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.3993. Min Act: -0.1700

Data Index: 877962 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.4618. Min Act: -0.1700

Data Index: 776191 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.3681. Min Act: -0.1700

Data Index: 1106724 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.3993. Min Act: -0.1700

Data Index: 305882 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.3368. Min Act: -0.1700

Data Index: 347030 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.3056. Min Act: -0.1700

Data Index: 1609393 (Python Code)

Max Activating Token Index: 560

Text #17

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.3056. Min Act: -0.1700

Data Index: 728988 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.3368. Min Act: -0.1700

Data Index: 73036 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.2743. Min Act: -0.1700

Data Index: 155714 (C4 (Web Text))

Max Activating Token Index: 728