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

Dataset: Open Web Text

Neuron 1764 in Layer 3

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: 4.0230. Min Range: -4.0230

Max Act: 4.0230. Min Act: -0.1700

Data Index: 7154146 (Open Web Text)

Max Activating Token Index: 683

Text #1

Max Range: 4.0230. Min Range: -4.0230

Max Act: 4.0115. Min Act: -0.1700

Data Index: 6255331 (Open Web Text)

Max Activating Token Index: 180

Text #2

Max Range: 4.0230. Min Range: -4.0230

Max Act: 3.9825. Min Act: -0.1700

Data Index: 6574779 (Open Web Text)

Max Activating Token Index: 493

Text #3

Max Range: 4.0230. Min Range: -4.0230

Max Act: 3.9608. Min Act: -0.1700

Data Index: 6432945 (Open Web Text)

Max Activating Token Index: 701

Text #4

Max Range: 4.0230. Min Range: -4.0230

Max Act: 3.9521. Min Act: -0.1700

Data Index: 5180738 (Open Web Text)

Max Activating Token Index: 181

Text #5

Max Range: 4.0230. Min Range: -4.0230

Max Act: 3.9368. Min Act: -0.1700

Data Index: 5002322 (Open Web Text)

Max Activating Token Index: 894

Text #6

Max Range: 4.0230. Min Range: -4.0230

Max Act: 3.9397. Min Act: -0.1700

Data Index: 7664561 (Open Web Text)

Max Activating Token Index: 201

Text #7

Max Range: 4.0230. Min Range: -4.0230

Max Act: 3.9450. Min Act: -0.1700

Data Index: 5728585 (Open Web Text)

Max Activating Token Index: 522

Text #8

Max Range: 4.0230. Min Range: -4.0230

Max Act: 3.9374. Min Act: -0.1700

Data Index: 4095473 (Open Web Text)

Max Activating Token Index: 557

Text #9

Max Range: 4.0230. Min Range: -4.0230

Max Act: 3.9176. Min Act: -0.1700

Data Index: 3328788 (Open Web Text)

Max Activating Token Index: 246

Text #10

Max Range: 4.0230. Min Range: -4.0230

Max Act: 3.9061. Min Act: -0.1700

Data Index: 1582736 (Open Web Text)

Max Activating Token Index: 213

Text #11

Max Range: 4.0230. Min Range: -4.0230

Max Act: 3.9198. Min Act: -0.1700

Data Index: 1689339 (Open Web Text)

Max Activating Token Index: 13

Text #12

Max Range: 4.0230. Min Range: -4.0230

Max Act: 3.8886. Min Act: -0.1700

Data Index: 4354596 (Open Web Text)

Max Activating Token Index: 520

Text #13

Max Range: 4.0230. Min Range: -4.0230

Max Act: 3.8577. Min Act: -0.1700

Data Index: 551378 (Open Web Text)

Max Activating Token Index: 772

Text #14

Max Range: 4.0230. Min Range: -4.0230

Max Act: 3.8934. Min Act: -0.1700

Data Index: 3743289 (Open Web Text)

Max Activating Token Index: 154

Text #15

Max Range: 4.0230. Min Range: -4.0230

Max Act: 3.8955. Min Act: -0.1700

Data Index: 1733260 (Open Web Text)

Max Activating Token Index: 250

Text #16

Max Range: 4.0230. Min Range: -4.0230

Max Act: 3.8906. Min Act: -0.1700

Data Index: 1078371 (Open Web Text)

Max Activating Token Index: 563

Text #17

Max Range: 4.0230. Min Range: -4.0230

Max Act: 3.8990. Min Act: -0.1700

Data Index: 6248983 (Open Web Text)

Max Activating Token Index: 206

Text #18

Max Range: 4.0230. Min Range: -4.0230

Max Act: 3.8879. Min Act: -0.1700

Data Index: 3319410 (Open Web Text)

Max Activating Token Index: 147

Text #19

Max Range: 4.0230. Min Range: -4.0230

Max Act: 3.8830. Min Act: -0.1700

Data Index: 3102855 (Open Web Text)

Max Activating Token Index: 231