Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1715 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6900. Min Range: -3.6900

Max Act: 3.6900. Min Act: -0.1700

Data Index: 1154187 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 3.6900. Min Range: -3.6900

Max Act: 3.6588. Min Act: -0.1700

Data Index: 510961 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 3.6900. Min Range: -3.6900

Max Act: 3.5648. Min Act: -0.1700

Data Index: 459318 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 3.6900. Min Range: -3.6900

Max Act: 3.5335. Min Act: -0.1700

Data Index: 954130 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 3.6900. Min Range: -3.6900

Max Act: 3.5022. Min Act: -0.1700

Data Index: 175351 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 3.6900. Min Range: -3.6900

Max Act: 3.4395. Min Act: -0.1700

Data Index: 185052 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 3.6900. Min Range: -3.6900

Max Act: 3.4395. Min Act: -0.1700

Data Index: 1336385 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 3.6900. Min Range: -3.6900

Max Act: 3.4238. Min Act: -0.1700

Data Index: 283241 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 3.6900. Min Range: -3.6900

Max Act: 3.4395. Min Act: -0.1700

Data Index: 188939 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 3.6900. Min Range: -3.6900

Max Act: 3.4081. Min Act: -0.1700

Data Index: 1076580 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 3.6900. Min Range: -3.6900

Max Act: 3.4081. Min Act: -0.1700

Data Index: 1103448 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 3.6900. Min Range: -3.6900

Max Act: 3.4081. Min Act: -0.1700

Data Index: 624483 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 3.6900. Min Range: -3.6900

Max Act: 3.4081. Min Act: -0.1700

Data Index: 1102820 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 3.6900. Min Range: -3.6900

Max Act: 3.3767. Min Act: -0.1700

Data Index: 1147066 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 3.6900. Min Range: -3.6900

Max Act: 3.3924. Min Act: -0.1700

Data Index: 1134795 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 3.6900. Min Range: -3.6900

Max Act: 3.3924. Min Act: -0.1700

Data Index: 1247183 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 3.6900. Min Range: -3.6900

Max Act: 3.3767. Min Act: -0.1700

Data Index: 1303624 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 3.6900. Min Range: -3.6900

Max Act: 3.3610. Min Act: -0.1700

Data Index: 1077231 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 3.6900. Min Range: -3.6900

Max Act: 3.3610. Min Act: -0.1700

Data Index: 360245 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 3.6900. Min Range: -3.6900

Max Act: 3.3453. Min Act: -0.1700

Data Index: 970934 (C4 (Web Text))

Max Activating Token Index: 8