Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1614 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.5152. Min Range: -4.5152

Max Act: 4.5152. Min Act: -0.1700

Data Index: 452967 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 4.5152. Min Range: -4.5152

Max Act: 4.4512. Min Act: -0.1700

Data Index: 134963 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 4.5152. Min Range: -4.5152

Max Act: 4.4478. Min Act: -0.1700

Data Index: 1226471 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 4.5152. Min Range: -4.5152

Max Act: 4.4729. Min Act: -0.1700

Data Index: 644137 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 4.5152. Min Range: -4.5152

Max Act: 4.4462. Min Act: -0.1700

Data Index: 587506 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 4.5152. Min Range: -4.5152

Max Act: 4.4241. Min Act: -0.1700

Data Index: 475545 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 4.5152. Min Range: -4.5152

Max Act: 4.4346. Min Act: -0.1700

Data Index: 986696 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 4.5152. Min Range: -4.5152

Max Act: 4.4338. Min Act: -0.1700

Data Index: 646938 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 4.5152. Min Range: -4.5152

Max Act: 4.4184. Min Act: -0.1700

Data Index: 996637 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 4.5152. Min Range: -4.5152

Max Act: 4.3800. Min Act: -0.1700

Data Index: 23114 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 4.5152. Min Range: -4.5152

Max Act: 4.3844. Min Act: -0.1700

Data Index: 133017 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 4.5152. Min Range: -4.5152

Max Act: 4.4050. Min Act: -0.1700

Data Index: 254927 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 4.5152. Min Range: -4.5152

Max Act: 4.3919. Min Act: -0.1700

Data Index: 225952 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 4.5152. Min Range: -4.5152

Max Act: 4.3853. Min Act: -0.1700

Data Index: 256901 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 4.5152. Min Range: -4.5152

Max Act: 4.3796. Min Act: -0.1700

Data Index: 1359576 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 4.5152. Min Range: -4.5152

Max Act: 4.3816. Min Act: -0.1700

Data Index: 717824 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 4.5152. Min Range: -4.5152

Max Act: 4.3844. Min Act: -0.1700

Data Index: 629239 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 4.5152. Min Range: -4.5152

Max Act: 4.3724. Min Act: -0.1700

Data Index: 262255 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 4.5152. Min Range: -4.5152

Max Act: 4.3872. Min Act: -0.1700

Data Index: 436229 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 4.5152. Min Range: -4.5152

Max Act: 4.3526. Min Act: -0.1700

Data Index: 728242 (C4 (Web Text))

Max Activating Token Index: 517