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

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

Neuron 40 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: 4.2781. Min Range: -4.2781

Max Act: 4.2781. Min Act: -0.1700

Data Index: 186825 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 4.2781. Min Range: -4.2781

Max Act: 4.1843. Min Act: -0.1700

Data Index: 193470 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 4.2781. Min Range: -4.2781

Max Act: 4.0280. Min Act: -0.1700

Data Index: 335194 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 4.2781. Min Range: -4.2781

Max Act: 4.0593. Min Act: -0.1700

Data Index: 422330 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 4.2781. Min Range: -4.2781

Max Act: 4.0280. Min Act: -0.1700

Data Index: 905643 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.9967. Min Act: -0.1700

Data Index: 280836 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.9967. Min Act: -0.1700

Data Index: 405445 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.9967. Min Act: -0.1700

Data Index: 29303 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 4.2781. Min Range: -4.2781

Max Act: 4.0280. Min Act: -0.1700

Data Index: 444002 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.9342. Min Act: -0.1700

Data Index: 860520 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.9967. Min Act: -0.1700

Data Index: 71169 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.9342. Min Act: -0.1700

Data Index: 561976 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.9186. Min Act: -0.1700

Data Index: 620960 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.9029. Min Act: -0.1700

Data Index: 6842 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.9186. Min Act: -0.1700

Data Index: 1173884 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.8873. Min Act: -0.1700

Data Index: 28708 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.9186. Min Act: -0.1700

Data Index: 125819 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.9186. Min Act: -0.1700

Data Index: 182851 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.8873. Min Act: -0.1700

Data Index: 1352924 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.9029. Min Act: -0.1700

Data Index: 717090 (C4 (Web Text))

Max Activating Token Index: 367