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

Dataset: Open Web Text

Neuron 1950 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: 4.5822. Min Range: -4.5822

Max Act: 4.5822. Min Act: -0.1700

Data Index: 7280003 (Open Web Text)

Max Activating Token Index: 294

Text #1

Max Range: 4.5822. Min Range: -4.5822

Max Act: 4.5188. Min Act: -0.1700

Data Index: 3040471 (Open Web Text)

Max Activating Token Index: 687

Text #2

Max Range: 4.5822. Min Range: -4.5822

Max Act: 4.4433. Min Act: -0.1700

Data Index: 5242829 (Open Web Text)

Max Activating Token Index: 434

Text #3

Max Range: 4.5822. Min Range: -4.5822

Max Act: 4.4259. Min Act: -0.1700

Data Index: 288373 (Open Web Text)

Max Activating Token Index: 872

Text #4

Max Range: 4.5822. Min Range: -4.5822

Max Act: 4.4239. Min Act: -0.1700

Data Index: 6179054 (Open Web Text)

Max Activating Token Index: 668

Text #5

Max Range: 4.5822. Min Range: -4.5822

Max Act: 4.4140. Min Act: -0.1700

Data Index: 7093296 (Open Web Text)

Max Activating Token Index: 395

Text #6

Max Range: 4.5822. Min Range: -4.5822

Max Act: 4.4187. Min Act: -0.1700

Data Index: 3340361 (Open Web Text)

Max Activating Token Index: 471

Text #7

Max Range: 4.5822. Min Range: -4.5822

Max Act: 4.3974. Min Act: -0.1700

Data Index: 120887 (Open Web Text)

Max Activating Token Index: 204

Text #8

Max Range: 4.5822. Min Range: -4.5822

Max Act: 4.3935. Min Act: -0.1700

Data Index: 5026217 (Open Web Text)

Max Activating Token Index: 636

Text #9

Max Range: 4.5822. Min Range: -4.5822

Max Act: 4.4317. Min Act: -0.1700

Data Index: 8049623 (Open Web Text)

Max Activating Token Index: 588

Text #10

Max Range: 4.5822. Min Range: -4.5822

Max Act: 4.3559. Min Act: -0.1700

Data Index: 2878350 (Open Web Text)

Max Activating Token Index: 946

Text #11

Max Range: 4.5822. Min Range: -4.5822

Max Act: 4.3841. Min Act: -0.1700

Data Index: 5080577 (Open Web Text)

Max Activating Token Index: 108

Text #12

Max Range: 4.5822. Min Range: -4.5822

Max Act: 4.3818. Min Act: -0.1700

Data Index: 223516 (Open Web Text)

Max Activating Token Index: 803

Text #13

Max Range: 4.5822. Min Range: -4.5822

Max Act: 4.3836. Min Act: -0.1700

Data Index: 3314849 (Open Web Text)

Max Activating Token Index: 513

Text #14

Max Range: 4.5822. Min Range: -4.5822

Max Act: 4.3741. Min Act: -0.1700

Data Index: 6852684 (Open Web Text)

Max Activating Token Index: 484

Text #15

Max Range: 4.5822. Min Range: -4.5822

Max Act: 4.3786. Min Act: -0.1700

Data Index: 4417415 (Open Web Text)

Max Activating Token Index: 691

Text #16

Max Range: 4.5822. Min Range: -4.5822

Max Act: 4.3513. Min Act: -0.1700

Data Index: 1613119 (Open Web Text)

Max Activating Token Index: 495

Text #17

Max Range: 4.5822. Min Range: -4.5822

Max Act: 4.3755. Min Act: -0.1700

Data Index: 5351400 (Open Web Text)

Max Activating Token Index: 416

Text #18

Max Range: 4.5822. Min Range: -4.5822

Max Act: 4.3889. Min Act: -0.1700

Data Index: 2489613 (Open Web Text)

Max Activating Token Index: 158

Text #19

Max Range: 4.5822. Min Range: -4.5822

Max Act: 4.3385. Min Act: -0.1700

Data Index: 6233796 (Open Web Text)

Max Activating Token Index: 133