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

Dataset: Open Web Text

Neuron 1703 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: 3.0301. Min Range: -3.0301

Max Act: 3.0301. Min Act: -0.1700

Data Index: 6275765 (Open Web Text)

Max Activating Token Index: 955

Text #1

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.9275. Min Act: -0.1700

Data Index: 6907402 (Open Web Text)

Max Activating Token Index: 115

Text #2

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.9422. Min Act: -0.1700

Data Index: 5082360 (Open Web Text)

Max Activating Token Index: 505

Text #3

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.9058. Min Act: -0.1700

Data Index: 3080302 (Open Web Text)

Max Activating Token Index: 778

Text #4

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.9022. Min Act: -0.1700

Data Index: 4188643 (Open Web Text)

Max Activating Token Index: 266

Text #5

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.8882. Min Act: -0.1700

Data Index: 396485 (Open Web Text)

Max Activating Token Index: 842

Text #6

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.8913. Min Act: -0.1700

Data Index: 8180706 (Open Web Text)

Max Activating Token Index: 606

Text #7

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.8901. Min Act: -0.1700

Data Index: 3773009 (Open Web Text)

Max Activating Token Index: 155

Text #8

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.8745. Min Act: -0.1700

Data Index: 730276 (Open Web Text)

Max Activating Token Index: 536

Text #9

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.8461. Min Act: -0.1700

Data Index: 2517737 (Open Web Text)

Max Activating Token Index: 72

Text #10

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.8546. Min Act: -0.1700

Data Index: 341657 (Open Web Text)

Max Activating Token Index: 621

Text #11

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.8327. Min Act: -0.1700

Data Index: 4096496 (Open Web Text)

Max Activating Token Index: 946

Text #12

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.8480. Min Act: -0.1700

Data Index: 2293786 (Open Web Text)

Max Activating Token Index: 440

Text #13

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.8468. Min Act: -0.1700

Data Index: 5539590 (Open Web Text)

Max Activating Token Index: 522

Text #14

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.8588. Min Act: -0.1700

Data Index: 7366939 (Open Web Text)

Max Activating Token Index: 625

Text #15

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.8273. Min Act: -0.1700

Data Index: 1456070 (Open Web Text)

Max Activating Token Index: 928

Text #16

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.8210. Min Act: -0.1700

Data Index: 2338041 (Open Web Text)

Max Activating Token Index: 552

Text #17

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.8206. Min Act: -0.1700

Data Index: 295782 (Open Web Text)

Max Activating Token Index: 531

Text #18

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.8161. Min Act: -0.1700

Data Index: 4198975 (Open Web Text)

Max Activating Token Index: 933

Text #19

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.8257. Min Act: -0.1700

Data Index: 5756885 (Open Web Text)

Max Activating Token Index: 657