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

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

Neuron 1242 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.2974. Min Act: -0.1700

Data Index: 26403 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.2817. Min Act: -0.1700

Data Index: 30952 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.2817. Min Act: -0.1700

Data Index: 47725 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.2503. Min Act: -0.1700

Data Index: 10700 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.2189. Min Act: -0.1700

Data Index: 145478 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.2189. Min Act: -0.1700

Data Index: 711920 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.2189. Min Act: -0.1700

Data Index: 1153199 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.2346. Min Act: -0.1700

Data Index: 358279 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.2189. Min Act: -0.1700

Data Index: 185151 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.2346. Min Act: -0.1700

Data Index: 765120 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.2346. Min Act: -0.1700

Data Index: 759348 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.2346. Min Act: -0.1700

Data Index: 1104839 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.1874. Min Act: -0.1700

Data Index: 159131 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.2031. Min Act: -0.1700

Data Index: 1162533 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.2189. Min Act: -0.1700

Data Index: 866476 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.2031. Min Act: -0.1700

Data Index: 1301648 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.2031. Min Act: -0.1700

Data Index: 806776 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.2346. Min Act: -0.1700

Data Index: 1071812 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.1874. Min Act: -0.1700

Data Index: 677189 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.1716. Min Act: -0.1700

Data Index: 1110311 (C4 (Web Text))

Max Activating Token Index: 984