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

Dataset: Open Web Text

Neuron 1603 in Layer 5

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: 4.8248. Min Range: -4.8248

Max Act: 4.8035. Min Act: -0.1700

Data Index: 8680927 (Open Web Text)

Max Activating Token Index: 344

Text #1

Max Range: 4.8248. Min Range: -4.8248

Max Act: 4.8248. Min Act: -0.1700

Data Index: 1090882 (Open Web Text)

Max Activating Token Index: 46

Text #2

Max Range: 4.8248. Min Range: -4.8248

Max Act: 4.7853. Min Act: -0.1700

Data Index: 870914 (Open Web Text)

Max Activating Token Index: 34

Text #3

Max Range: 4.8248. Min Range: -4.8248

Max Act: 4.7298. Min Act: -0.1700

Data Index: 6319213 (Open Web Text)

Max Activating Token Index: 212

Text #4

Max Range: 4.8248. Min Range: -4.8248

Max Act: 4.7328. Min Act: -0.1700

Data Index: 3100003 (Open Web Text)

Max Activating Token Index: 454

Text #5

Max Range: 4.8248. Min Range: -4.8248

Max Act: 4.7078. Min Act: -0.1700

Data Index: 8631983 (Open Web Text)

Max Activating Token Index: 77

Text #6

Max Range: 4.8248. Min Range: -4.8248

Max Act: 4.7115. Min Act: -0.1700

Data Index: 561558 (Open Web Text)

Max Activating Token Index: 172

Text #7

Max Range: 4.8248. Min Range: -4.8248

Max Act: 4.7360. Min Act: -0.1700

Data Index: 3929872 (Open Web Text)

Max Activating Token Index: 253

Text #8

Max Range: 4.8248. Min Range: -4.8248

Max Act: 4.6672. Min Act: -0.1700

Data Index: 6182984 (Open Web Text)

Max Activating Token Index: 80

Text #9

Max Range: 4.8248. Min Range: -4.8248

Max Act: 4.6786. Min Act: -0.1700

Data Index: 3493798 (Open Web Text)

Max Activating Token Index: 51

Text #10

Max Range: 4.8248. Min Range: -4.8248

Max Act: 4.6314. Min Act: -0.1700

Data Index: 7649315 (Open Web Text)

Max Activating Token Index: 531

Text #11

Max Range: 4.8248. Min Range: -4.8248

Max Act: 4.6501. Min Act: -0.1700

Data Index: 2034030 (Open Web Text)

Max Activating Token Index: 186

Text #12

Max Range: 4.8248. Min Range: -4.8248

Max Act: 4.6701. Min Act: -0.1700

Data Index: 8680930 (Open Web Text)

Max Activating Token Index: 46

Text #13

Max Range: 4.8248. Min Range: -4.8248

Max Act: 4.6463. Min Act: -0.1700

Data Index: 7014406 (Open Web Text)

Max Activating Token Index: 19

Text #14

Max Range: 4.8248. Min Range: -4.8248

Max Act: 4.6459. Min Act: -0.1700

Data Index: 7266315 (Open Web Text)

Max Activating Token Index: 275

Text #15

Max Range: 4.8248. Min Range: -4.8248

Max Act: 4.6518. Min Act: -0.1700

Data Index: 1436667 (Open Web Text)

Max Activating Token Index: 51

Text #16

Max Range: 4.8248. Min Range: -4.8248

Max Act: 4.6542. Min Act: -0.1700

Data Index: 3463359 (Open Web Text)

Max Activating Token Index: 188

Text #17

Max Range: 4.8248. Min Range: -4.8248

Max Act: 4.6345. Min Act: -0.1700

Data Index: 8282999 (Open Web Text)

Max Activating Token Index: 120

Text #18

Max Range: 4.8248. Min Range: -4.8248

Max Act: 4.6482. Min Act: -0.1700

Data Index: 7014407 (Open Web Text)

Max Activating Token Index: 42

Text #19

Max Range: 4.8248. Min Range: -4.8248

Max Act: 4.6535. Min Act: -0.1700

Data Index: 4164298 (Open Web Text)

Max Activating Token Index: 372