Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1612 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 5.0156. Min Range: -5.0156

Max Act: 5.0119. Min Act: -0.1700

Data Index: 8141718 (Open Web Text)

Max Activating Token Index: 189

Text #1

Max Range: 5.0156. Min Range: -5.0156

Max Act: 5.0156. Min Act: -0.1700

Data Index: 982691 (Open Web Text)

Max Activating Token Index: 22

Text #2

Max Range: 5.0156. Min Range: -5.0156

Max Act: 4.9762. Min Act: -0.1700

Data Index: 8700497 (Open Web Text)

Max Activating Token Index: 572

Text #3

Max Range: 5.0156. Min Range: -5.0156

Max Act: 4.9219. Min Act: -0.1700

Data Index: 4378448 (Open Web Text)

Max Activating Token Index: 30

Text #4

Max Range: 5.0156. Min Range: -5.0156

Max Act: 4.9230. Min Act: -0.1700

Data Index: 1513024 (Open Web Text)

Max Activating Token Index: 518

Text #5

Max Range: 5.0156. Min Range: -5.0156

Max Act: 4.9208. Min Act: -0.1700

Data Index: 5527384 (Open Web Text)

Max Activating Token Index: 397

Text #6

Max Range: 5.0156. Min Range: -5.0156

Max Act: 4.9162. Min Act: -0.1700

Data Index: 3077743 (Open Web Text)

Max Activating Token Index: 174

Text #7

Max Range: 5.0156. Min Range: -5.0156

Max Act: 4.9242. Min Act: -0.1700

Data Index: 2888099 (Open Web Text)

Max Activating Token Index: 163

Text #8

Max Range: 5.0156. Min Range: -5.0156

Max Act: 4.9329. Min Act: -0.1700

Data Index: 2686705 (Open Web Text)

Max Activating Token Index: 475

Text #9

Max Range: 5.0156. Min Range: -5.0156

Max Act: 4.9105. Min Act: -0.1700

Data Index: 2675638 (Open Web Text)

Max Activating Token Index: 444

Text #10

Max Range: 5.0156. Min Range: -5.0156

Max Act: 4.8821. Min Act: -0.1700

Data Index: 2440254 (Open Web Text)

Max Activating Token Index: 538

Text #11

Max Range: 5.0156. Min Range: -5.0156

Max Act: 4.8938. Min Act: -0.1700

Data Index: 955818 (Open Web Text)

Max Activating Token Index: 457

Text #12

Max Range: 5.0156. Min Range: -5.0156

Max Act: 4.8983. Min Act: -0.1700

Data Index: 4599677 (Open Web Text)

Max Activating Token Index: 758

Text #13

Max Range: 5.0156. Min Range: -5.0156

Max Act: 4.9067. Min Act: -0.1700

Data Index: 4434226 (Open Web Text)

Max Activating Token Index: 419

Text #14

Max Range: 5.0156. Min Range: -5.0156

Max Act: 4.8778. Min Act: -0.1700

Data Index: 2002131 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 5.0156. Min Range: -5.0156

Max Act: 4.8795. Min Act: -0.1700

Data Index: 5677792 (Open Web Text)

Max Activating Token Index: 23

Text #16

Max Range: 5.0156. Min Range: -5.0156

Max Act: 4.8765. Min Act: -0.1700

Data Index: 7164657 (Open Web Text)

Max Activating Token Index: 172

Text #17

Max Range: 5.0156. Min Range: -5.0156

Max Act: 4.8753. Min Act: -0.1700

Data Index: 3976541 (Open Web Text)

Max Activating Token Index: 789

Text #18

Max Range: 5.0156. Min Range: -5.0156

Max Act: 4.8895. Min Act: -0.1700

Data Index: 4365815 (Open Web Text)

Max Activating Token Index: 136

Text #19

Max Range: 5.0156. Min Range: -5.0156

Max Act: 4.8499. Min Act: -0.1700

Data Index: 7028258 (Open Web Text)

Max Activating Token Index: 721