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

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

Neuron 1627 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: 5.6913. Min Range: -5.6913

Max Act: 5.6913. Min Act: -0.1700

Data Index: 328875 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 5.6913. Min Range: -5.6913

Max Act: 5.6288. Min Act: -0.1700

Data Index: 844561 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 5.6913. Min Range: -5.6913

Max Act: 5.5663. Min Act: -0.1700

Data Index: 1269503 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 5.6913. Min Range: -5.6913

Max Act: 5.5350. Min Act: -0.1700

Data Index: 931821 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 5.6913. Min Range: -5.6913

Max Act: 5.5663. Min Act: -0.1700

Data Index: 603664 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 5.6913. Min Range: -5.6913

Max Act: 5.5350. Min Act: -0.1700

Data Index: 675659 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 5.6913. Min Range: -5.6913

Max Act: 5.5350. Min Act: -0.1700

Data Index: 1045529 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 5.6913. Min Range: -5.6913

Max Act: 5.5038. Min Act: -0.1700

Data Index: 22049 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 5.6913. Min Range: -5.6913

Max Act: 5.5038. Min Act: -0.1700

Data Index: 506789 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 5.6913. Min Range: -5.6913

Max Act: 5.4725. Min Act: -0.1700

Data Index: 1135579 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 5.6913. Min Range: -5.6913

Max Act: 5.4413. Min Act: -0.1700

Data Index: 173030 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 5.6913. Min Range: -5.6913

Max Act: 5.4100. Min Act: -0.1700

Data Index: 626138 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 5.6913. Min Range: -5.6913

Max Act: 5.4413. Min Act: -0.1700

Data Index: 512799 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 5.6913. Min Range: -5.6913

Max Act: 5.4100. Min Act: -0.1700

Data Index: 168610 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 5.6913. Min Range: -5.6913

Max Act: 5.3788. Min Act: -0.1700

Data Index: 302118 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 5.6913. Min Range: -5.6913

Max Act: 5.4100. Min Act: -0.1700

Data Index: 421095 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 5.6913. Min Range: -5.6913

Max Act: 5.3788. Min Act: -0.1700

Data Index: 607170 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 5.6913. Min Range: -5.6913

Max Act: 5.3788. Min Act: -0.1700

Data Index: 445967 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 5.6913. Min Range: -5.6913

Max Act: 5.4100. Min Act: -0.1700

Data Index: 470741 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 5.6913. Min Range: -5.6913

Max Act: 5.3788. Min Act: -0.1700

Data Index: 379278 (C4 (Web Text))

Max Activating Token Index: 375