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

Dataset: Open Web Text

Neuron 2020 in Layer 0

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: 4.0168. Min Range: -4.0168

Max Act: 4.0168. Min Act: -0.1700

Data Index: 3741331 (Open Web Text)

Max Activating Token Index: 905

Text #1

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.8918. Min Act: -0.1700

Data Index: 7220571 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.8873. Min Act: -0.1700

Data Index: 5027787 (Open Web Text)

Max Activating Token Index: 54

Text #3

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.8537. Min Act: -0.1700

Data Index: 6069600 (Open Web Text)

Max Activating Token Index: 72

Text #4

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.8783. Min Act: -0.1700

Data Index: 5970158 (Open Web Text)

Max Activating Token Index: 38

Text #5

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.8720. Min Act: -0.1700

Data Index: 3909544 (Open Web Text)

Max Activating Token Index: 950

Text #6

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.8743. Min Act: -0.1700

Data Index: 6643276 (Open Web Text)

Max Activating Token Index: 374

Text #7

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.8415. Min Act: -0.1700

Data Index: 1180240 (Open Web Text)

Max Activating Token Index: 1012

Text #8

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.8309. Min Act: -0.1700

Data Index: 7899491 (Open Web Text)

Max Activating Token Index: 231

Text #9

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.8332. Min Act: -0.1700

Data Index: 5830973 (Open Web Text)

Max Activating Token Index: 439

Text #10

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.8208. Min Act: -0.1700

Data Index: 7576832 (Open Web Text)

Max Activating Token Index: 355

Text #11

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.8341. Min Act: -0.1700

Data Index: 5078452 (Open Web Text)

Max Activating Token Index: 56

Text #12

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.8151. Min Act: -0.1700

Data Index: 5034379 (Open Web Text)

Max Activating Token Index: 493

Text #13

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.8162. Min Act: -0.1700

Data Index: 2484222 (Open Web Text)

Max Activating Token Index: 151

Text #14

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.8374. Min Act: -0.1700

Data Index: 7111518 (Open Web Text)

Max Activating Token Index: 437

Text #15

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.8393. Min Act: -0.1700

Data Index: 6489393 (Open Web Text)

Max Activating Token Index: 827

Text #16

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.8268. Min Act: -0.1700

Data Index: 1873228 (Open Web Text)

Max Activating Token Index: 738

Text #17

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.8363. Min Act: -0.1700

Data Index: 6223978 (Open Web Text)

Max Activating Token Index: 320

Text #18

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.8248. Min Act: -0.1700

Data Index: 3863629 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.8452. Min Act: -0.1700

Data Index: 3807269 (Open Web Text)

Max Activating Token Index: 4