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

Dataset: Open Web Text

Neuron 2857 in Layer 1

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: 1.6751. Min Range: -1.6751

Max Act: 1.6751. Min Act: -0.1700

Data Index: 2622195 (Open Web Text)

Max Activating Token Index: 174

Text #1

Max Range: 1.6751. Min Range: -1.6751

Max Act: 1.6258. Min Act: -0.1700

Data Index: 1695034 (Open Web Text)

Max Activating Token Index: 547

Text #2

Max Range: 1.6751. Min Range: -1.6751

Max Act: 1.6207. Min Act: -0.1700

Data Index: 6444338 (Open Web Text)

Max Activating Token Index: 413

Text #3

Max Range: 1.6751. Min Range: -1.6751

Max Act: 1.6166. Min Act: -0.1700

Data Index: 7378292 (Open Web Text)

Max Activating Token Index: 289

Text #4

Max Range: 1.6751. Min Range: -1.6751

Max Act: 1.6200. Min Act: -0.1700

Data Index: 3969764 (Open Web Text)

Max Activating Token Index: 490

Text #5

Max Range: 1.6751. Min Range: -1.6751

Max Act: 1.6054. Min Act: -0.1700

Data Index: 6129992 (Open Web Text)

Max Activating Token Index: 282

Text #6

Max Range: 1.6751. Min Range: -1.6751

Max Act: 1.6091. Min Act: -0.1700

Data Index: 1958261 (Open Web Text)

Max Activating Token Index: 917

Text #7

Max Range: 1.6751. Min Range: -1.6751

Max Act: 1.6110. Min Act: -0.1700

Data Index: 7045723 (Open Web Text)

Max Activating Token Index: 46

Text #8

Max Range: 1.6751. Min Range: -1.6751

Max Act: 1.5927. Min Act: -0.1700

Data Index: 4968879 (Open Web Text)

Max Activating Token Index: 414

Text #9

Max Range: 1.6751. Min Range: -1.6751

Max Act: 1.5813. Min Act: -0.1700

Data Index: 2856106 (Open Web Text)

Max Activating Token Index: 552

Text #10

Max Range: 1.6751. Min Range: -1.6751

Max Act: 1.5750. Min Act: -0.1699

Data Index: 4785660 (Open Web Text)

Max Activating Token Index: 503

Text #11

Max Range: 1.6751. Min Range: -1.6751

Max Act: 1.5936. Min Act: -0.1700

Data Index: 6082248 (Open Web Text)

Max Activating Token Index: 420

Text #12

Max Range: 1.6751. Min Range: -1.6751

Max Act: 1.5855. Min Act: -0.1700

Data Index: 7343936 (Open Web Text)

Max Activating Token Index: 688

Text #13

Max Range: 1.6751. Min Range: -1.6751

Max Act: 1.5785. Min Act: -0.1700

Data Index: 4705238 (Open Web Text)

Max Activating Token Index: 170

Text #14

Max Range: 1.6751. Min Range: -1.6751

Max Act: 1.5772. Min Act: -0.1700

Data Index: 2708570 (Open Web Text)

Max Activating Token Index: 108

Text #15

Max Range: 1.6751. Min Range: -1.6751

Max Act: 1.5753. Min Act: -0.1700

Data Index: 6515243 (Open Web Text)

Max Activating Token Index: 179

Text #16

Max Range: 1.6751. Min Range: -1.6751

Max Act: 1.5710. Min Act: -0.1700

Data Index: 5493692 (Open Web Text)

Max Activating Token Index: 482

Text #17

Max Range: 1.6751. Min Range: -1.6751

Max Act: 1.5554. Min Act: -0.1699

Data Index: 4646896 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 1.6751. Min Range: -1.6751

Max Act: 1.5595. Min Act: -0.1698

Data Index: 6448605 (Open Web Text)

Max Activating Token Index: 399

Text #19

Max Range: 1.6751. Min Range: -1.6751

Max Act: 1.5638. Min Act: -0.1700

Data Index: 8454889 (Open Web Text)

Max Activating Token Index: 515