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

Dataset: Open Web Text

Neuron 1396 in Layer 4

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: 7.5196. Min Range: -7.5196

Max Act: 7.5196. Min Act: -0.1700

Data Index: 5899002 (Open Web Text)

Max Activating Token Index: 907

Text #1

Max Range: 7.5196. Min Range: -7.5196

Max Act: 7.5030. Min Act: -0.1700

Data Index: 5799174 (Open Web Text)

Max Activating Token Index: 745

Text #2

Max Range: 7.5196. Min Range: -7.5196

Max Act: 7.3871. Min Act: -0.1700

Data Index: 6999626 (Open Web Text)

Max Activating Token Index: 1002

Text #3

Max Range: 7.5196. Min Range: -7.5196

Max Act: 7.4557. Min Act: -0.1700

Data Index: 8702414 (Open Web Text)

Max Activating Token Index: 355

Text #4

Max Range: 7.5196. Min Range: -7.5196

Max Act: 7.2138. Min Act: -0.1700

Data Index: 1514342 (Open Web Text)

Max Activating Token Index: 463

Text #5

Max Range: 7.5196. Min Range: -7.5196

Max Act: 7.2965. Min Act: -0.1700

Data Index: 5412150 (Open Web Text)

Max Activating Token Index: 944

Text #6

Max Range: 7.5196. Min Range: -7.5196

Max Act: 7.2471. Min Act: -0.1700

Data Index: 819760 (Open Web Text)

Max Activating Token Index: 161

Text #7

Max Range: 7.5196. Min Range: -7.5196

Max Act: 7.2266. Min Act: -0.1700

Data Index: 2358188 (Open Web Text)

Max Activating Token Index: 181

Text #8

Max Range: 7.5196. Min Range: -7.5196

Max Act: 7.2302. Min Act: -0.1697

Data Index: 7139813 (Open Web Text)

Max Activating Token Index: 386

Text #9

Max Range: 7.5196. Min Range: -7.5196

Max Act: 7.1958. Min Act: -0.1700

Data Index: 8373707 (Open Web Text)

Max Activating Token Index: 280

Text #10

Max Range: 7.5196. Min Range: -7.5196

Max Act: 7.1965. Min Act: -0.1699

Data Index: 8177987 (Open Web Text)

Max Activating Token Index: 187

Text #11

Max Range: 7.5196. Min Range: -7.5196

Max Act: 7.2175. Min Act: -0.1700

Data Index: 7524469 (Open Web Text)

Max Activating Token Index: 582

Text #12

Max Range: 7.5196. Min Range: -7.5196

Max Act: 7.2456. Min Act: -0.1700

Data Index: 2755842 (Open Web Text)

Max Activating Token Index: 517

Text #13

Max Range: 7.5196. Min Range: -7.5196

Max Act: 7.1476. Min Act: -0.1700

Data Index: 2570104 (Open Web Text)

Max Activating Token Index: 433

Text #14

Max Range: 7.5196. Min Range: -7.5196

Max Act: 7.0838. Min Act: -0.1700

Data Index: 6895287 (Open Web Text)

Max Activating Token Index: 386

Text #15

Max Range: 7.5196. Min Range: -7.5196

Max Act: 7.1757. Min Act: -0.1700

Data Index: 6895969 (Open Web Text)

Max Activating Token Index: 963

Text #16

Max Range: 7.5196. Min Range: -7.5196

Max Act: 7.1498. Min Act: -0.1700

Data Index: 2364460 (Open Web Text)

Max Activating Token Index: 866

Text #17

Max Range: 7.5196. Min Range: -7.5196

Max Act: 7.1187. Min Act: -0.1699

Data Index: 8298491 (Open Web Text)

Max Activating Token Index: 294

Text #18

Max Range: 7.5196. Min Range: -7.5196

Max Act: 7.1008. Min Act: -0.1700

Data Index: 1225416 (Open Web Text)

Max Activating Token Index: 720

Text #19

Max Range: 7.5196. Min Range: -7.5196

Max Act: 7.0774. Min Act: -0.1700

Data Index: 3639281 (Open Web Text)

Max Activating Token Index: 299