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

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

Neuron 1111 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: 3.5042. Min Range: -3.5042

Max Act: 3.5042. Min Act: -0.1700

Data Index: 1052514 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.4415. Min Act: -0.1700

Data Index: 608578 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.4101. Min Act: -0.1700

Data Index: 480760 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.4101. Min Act: -0.1700

Data Index: 1344885 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.3944. Min Act: -0.1700

Data Index: 220714 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.3944. Min Act: -0.1700

Data Index: 643648 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.3787. Min Act: -0.1700

Data Index: 1029849 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.3787. Min Act: -0.1700

Data Index: 1131141 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.4101. Min Act: -0.1700

Data Index: 888501 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.3473. Min Act: -0.1700

Data Index: 12340 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.3630. Min Act: -0.1700

Data Index: 1044176 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.3159. Min Act: -0.1700

Data Index: 548545 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.3473. Min Act: -0.1700

Data Index: 58902 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.3630. Min Act: -0.1700

Data Index: 1031820 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.3630. Min Act: -0.1700

Data Index: 444722 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.3630. Min Act: -0.1700

Data Index: 985759 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.3159. Min Act: -0.1700

Data Index: 929299 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.3630. Min Act: -0.1700

Data Index: 1155467 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.3630. Min Act: -0.1700

Data Index: 531327 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.3316. Min Act: -0.1700

Data Index: 968094 (C4 (Web Text))

Max Activating Token Index: 392