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

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

Neuron 1042 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5933. Min Range: -3.5933

Max Act: 3.5933. Min Act: -0.1700

Data Index: 1467844 (Python Code)

Max Activating Token Index: 141

Text #1

Max Range: 3.5933. Min Range: -3.5933

Max Act: 3.5620. Min Act: -0.1700

Data Index: 116249 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 3.5933. Min Range: -3.5933

Max Act: 3.4993. Min Act: -0.1700

Data Index: 1292881 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 3.5933. Min Range: -3.5933

Max Act: 3.5620. Min Act: -0.1700

Data Index: 411749 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 3.5933. Min Range: -3.5933

Max Act: 3.5306. Min Act: -0.1700

Data Index: 828276 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 3.5933. Min Range: -3.5933

Max Act: 3.4993. Min Act: -0.1700

Data Index: 689117 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 3.5933. Min Range: -3.5933

Max Act: 3.5306. Min Act: -0.1700

Data Index: 402031 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 3.5933. Min Range: -3.5933

Max Act: 3.4993. Min Act: -0.1700

Data Index: 832897 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 3.5933. Min Range: -3.5933

Max Act: 3.4366. Min Act: -0.1700

Data Index: 222590 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 3.5933. Min Range: -3.5933

Max Act: 3.4366. Min Act: -0.1700

Data Index: 861657 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 3.5933. Min Range: -3.5933

Max Act: 3.4680. Min Act: -0.1700

Data Index: 671873 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 3.5933. Min Range: -3.5933

Max Act: 3.4366. Min Act: -0.1700

Data Index: 416593 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.5933. Min Range: -3.5933

Max Act: 3.4680. Min Act: -0.1700

Data Index: 1237833 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 3.5933. Min Range: -3.5933

Max Act: 3.4680. Min Act: -0.1700

Data Index: 1044511 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 3.5933. Min Range: -3.5933

Max Act: 3.4680. Min Act: -0.1700

Data Index: 913247 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 3.5933. Min Range: -3.5933

Max Act: 3.4680. Min Act: -0.1700

Data Index: 759691 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 3.5933. Min Range: -3.5933

Max Act: 3.4052. Min Act: -0.1700

Data Index: 996729 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 3.5933. Min Range: -3.5933

Max Act: 3.4366. Min Act: -0.1700

Data Index: 365868 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 3.5933. Min Range: -3.5933

Max Act: 3.4366. Min Act: -0.1700

Data Index: 454033 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.5933. Min Range: -3.5933

Max Act: 3.4366. Min Act: -0.1700

Data Index: 832194 (C4 (Web Text))

Max Activating Token Index: 603