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

Dataset: Open Web Text

Neuron 1446 in Layer 0

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: 4.2931. Min Range: -4.2931

Max Act: 4.2931. Min Act: -0.1700

Data Index: 1452333 (Open Web Text)

Max Activating Token Index: 765

Text #1

Max Range: 4.2931. Min Range: -4.2931

Max Act: 4.2709. Min Act: -0.1700

Data Index: 2312925 (Open Web Text)

Max Activating Token Index: 137

Text #2

Max Range: 4.2931. Min Range: -4.2931

Max Act: 4.2720. Min Act: -0.1700

Data Index: 2312926 (Open Web Text)

Max Activating Token Index: 961

Text #3

Max Range: 4.2931. Min Range: -4.2931

Max Act: 4.2583. Min Act: -0.1700

Data Index: 6832836 (Open Web Text)

Max Activating Token Index: 393

Text #4

Max Range: 4.2931. Min Range: -4.2931

Max Act: 4.2291. Min Act: -0.1700

Data Index: 4638812 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 4.2931. Min Range: -4.2931

Max Act: 4.2272. Min Act: -0.1700

Data Index: 5414419 (Open Web Text)

Max Activating Token Index: 915

Text #6

Max Range: 4.2931. Min Range: -4.2931

Max Act: 4.1819. Min Act: -0.1700

Data Index: 1362362 (Open Web Text)

Max Activating Token Index: 54

Text #7

Max Range: 4.2931. Min Range: -4.2931

Max Act: 4.1895. Min Act: -0.1700

Data Index: 4221930 (Open Web Text)

Max Activating Token Index: 133

Text #8

Max Range: 4.2931. Min Range: -4.2931

Max Act: 4.2161. Min Act: -0.1700

Data Index: 3711378 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 4.2931. Min Range: -4.2931

Max Act: 4.1749. Min Act: -0.1700

Data Index: 3786631 (Open Web Text)

Max Activating Token Index: 1011

Text #10

Max Range: 4.2931. Min Range: -4.2931

Max Act: 4.1973. Min Act: -0.1700

Data Index: 5740998 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.2931. Min Range: -4.2931

Max Act: 4.1739. Min Act: -0.1700

Data Index: 2119524 (Open Web Text)

Max Activating Token Index: 18

Text #12

Max Range: 4.2931. Min Range: -4.2931

Max Act: 4.1210. Min Act: -0.1700

Data Index: 17353 (Open Web Text)

Max Activating Token Index: 247

Text #13

Max Range: 4.2931. Min Range: -4.2931

Max Act: 4.1119. Min Act: -0.1700

Data Index: 6629453 (Open Web Text)

Max Activating Token Index: 916

Text #14

Max Range: 4.2931. Min Range: -4.2931

Max Act: 4.1349. Min Act: -0.1700

Data Index: 7223145 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.2931. Min Range: -4.2931

Max Act: 4.1420. Min Act: -0.1700

Data Index: 338386 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.2931. Min Range: -4.2931

Max Act: 4.1314. Min Act: -0.1700

Data Index: 7517882 (Open Web Text)

Max Activating Token Index: 682

Text #17

Max Range: 4.2931. Min Range: -4.2931

Max Act: 4.1440. Min Act: -0.1700

Data Index: 7746627 (Open Web Text)

Max Activating Token Index: 27

Text #18

Max Range: 4.2931. Min Range: -4.2931

Max Act: 4.1536. Min Act: -0.1700

Data Index: 4995331 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.2931. Min Range: -4.2931

Max Act: 4.1276. Min Act: -0.1700

Data Index: 5619602 (Open Web Text)

Max Activating Token Index: 27