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

Dataset: Open Web Text

Neuron 1062 in Layer 6

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: 5.4142. Min Range: -5.4142

Max Act: 5.4142. Min Act: -0.1700

Data Index: 5674682 (Open Web Text)

Max Activating Token Index: 940

Text #1

Max Range: 5.4142. Min Range: -5.4142

Max Act: 5.3063. Min Act: -0.1700

Data Index: 7710858 (Open Web Text)

Max Activating Token Index: 768

Text #2

Max Range: 5.4142. Min Range: -5.4142

Max Act: 5.2347. Min Act: -0.1700

Data Index: 7013929 (Open Web Text)

Max Activating Token Index: 520

Text #3

Max Range: 5.4142. Min Range: -5.4142

Max Act: 5.2135. Min Act: -0.1700

Data Index: 326602 (Open Web Text)

Max Activating Token Index: 906

Text #4

Max Range: 5.4142. Min Range: -5.4142

Max Act: 5.1947. Min Act: -0.1700

Data Index: 3578293 (Open Web Text)

Max Activating Token Index: 512

Text #5

Max Range: 5.4142. Min Range: -5.4142

Max Act: 5.1579. Min Act: -0.1700

Data Index: 22253 (Open Web Text)

Max Activating Token Index: 831

Text #6

Max Range: 5.4142. Min Range: -5.4142

Max Act: 5.1582. Min Act: -0.1700

Data Index: 5473225 (Open Web Text)

Max Activating Token Index: 903

Text #7

Max Range: 5.4142. Min Range: -5.4142

Max Act: 5.1400. Min Act: -0.1700

Data Index: 2818511 (Open Web Text)

Max Activating Token Index: 311

Text #8

Max Range: 5.4142. Min Range: -5.4142

Max Act: 5.1264. Min Act: -0.1700

Data Index: 5403803 (Open Web Text)

Max Activating Token Index: 229

Text #9

Max Range: 5.4142. Min Range: -5.4142

Max Act: 5.0658. Min Act: -0.1700

Data Index: 5040220 (Open Web Text)

Max Activating Token Index: 293

Text #10

Max Range: 5.4142. Min Range: -5.4142

Max Act: 5.0393. Min Act: -0.1700

Data Index: 816566 (Open Web Text)

Max Activating Token Index: 22

Text #11

Max Range: 5.4142. Min Range: -5.4142

Max Act: 5.0552. Min Act: -0.1700

Data Index: 8818427 (Open Web Text)

Max Activating Token Index: 879

Text #12

Max Range: 5.4142. Min Range: -5.4142

Max Act: 5.0314. Min Act: -0.1700

Data Index: 6937472 (Open Web Text)

Max Activating Token Index: 479

Text #13

Max Range: 5.4142. Min Range: -5.4142

Max Act: 5.0661. Min Act: -0.1700

Data Index: 2529277 (Open Web Text)

Max Activating Token Index: 823

Text #14

Max Range: 5.4142. Min Range: -5.4142

Max Act: 5.0042. Min Act: -0.1700

Data Index: 3078238 (Open Web Text)

Max Activating Token Index: 240

Text #15

Max Range: 5.4142. Min Range: -5.4142

Max Act: 4.9605. Min Act: -0.1700

Data Index: 6729379 (Open Web Text)

Max Activating Token Index: 547

Text #16

Max Range: 5.4142. Min Range: -5.4142

Max Act: 5.0004. Min Act: -0.1700

Data Index: 6785927 (Open Web Text)

Max Activating Token Index: 239

Text #17

Max Range: 5.4142. Min Range: -5.4142

Max Act: 4.9758. Min Act: -0.1700

Data Index: 3943840 (Open Web Text)

Max Activating Token Index: 267

Text #18

Max Range: 5.4142. Min Range: -5.4142

Max Act: 4.9856. Min Act: -0.1700

Data Index: 7667327 (Open Web Text)

Max Activating Token Index: 961

Text #19

Max Range: 5.4142. Min Range: -5.4142

Max Act: 4.9648. Min Act: -0.1700

Data Index: 3327822 (Open Web Text)

Max Activating Token Index: 95