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

Dataset: Open Web Text

Neuron 2038 in Layer 2

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: 3.5911. Min Range: -3.5911

Max Act: 3.5783. Min Act: -0.1700

Data Index: 1341736 (Open Web Text)

Max Activating Token Index: 20

Text #1

Max Range: 3.5911. Min Range: -3.5911

Max Act: 3.5911. Min Act: -0.1700

Data Index: 7365857 (Open Web Text)

Max Activating Token Index: 892

Text #2

Max Range: 3.5911. Min Range: -3.5911

Max Act: 3.5598. Min Act: -0.1700

Data Index: 2481852 (Open Web Text)

Max Activating Token Index: 420

Text #3

Max Range: 3.5911. Min Range: -3.5911

Max Act: 3.5624. Min Act: -0.1700

Data Index: 2202836 (Open Web Text)

Max Activating Token Index: 296

Text #4

Max Range: 3.5911. Min Range: -3.5911

Max Act: 3.5323. Min Act: -0.1700

Data Index: 1706055 (Open Web Text)

Max Activating Token Index: 641

Text #5

Max Range: 3.5911. Min Range: -3.5911

Max Act: 3.5452. Min Act: -0.1700

Data Index: 1245403 (Open Web Text)

Max Activating Token Index: 402

Text #6

Max Range: 3.5911. Min Range: -3.5911

Max Act: 3.5519. Min Act: -0.1700

Data Index: 6225445 (Open Web Text)

Max Activating Token Index: 835

Text #7

Max Range: 3.5911. Min Range: -3.5911

Max Act: 3.5477. Min Act: -0.1700

Data Index: 926880 (Open Web Text)

Max Activating Token Index: 26

Text #8

Max Range: 3.5911. Min Range: -3.5911

Max Act: 3.5412. Min Act: -0.1700

Data Index: 4112531 (Open Web Text)

Max Activating Token Index: 109

Text #9

Max Range: 3.5911. Min Range: -3.5911

Max Act: 3.5303. Min Act: -0.1700

Data Index: 811882 (Open Web Text)

Max Activating Token Index: 17

Text #10

Max Range: 3.5911. Min Range: -3.5911

Max Act: 3.5110. Min Act: -0.1700

Data Index: 7193500 (Open Web Text)

Max Activating Token Index: 434

Text #11

Max Range: 3.5911. Min Range: -3.5911

Max Act: 3.5157. Min Act: -0.1700

Data Index: 5160963 (Open Web Text)

Max Activating Token Index: 361

Text #12

Max Range: 3.5911. Min Range: -3.5911

Max Act: 3.4884. Min Act: -0.1700

Data Index: 5131843 (Open Web Text)

Max Activating Token Index: 633

Text #13

Max Range: 3.5911. Min Range: -3.5911

Max Act: 3.4969. Min Act: -0.1700

Data Index: 3291400 (Open Web Text)

Max Activating Token Index: 33

Text #14

Max Range: 3.5911. Min Range: -3.5911

Max Act: 3.5130. Min Act: -0.1700

Data Index: 8238993 (Open Web Text)

Max Activating Token Index: 970

Text #15

Max Range: 3.5911. Min Range: -3.5911

Max Act: 3.4981. Min Act: -0.1700

Data Index: 8703390 (Open Web Text)

Max Activating Token Index: 171

Text #16

Max Range: 3.5911. Min Range: -3.5911

Max Act: 3.5136. Min Act: -0.1700

Data Index: 8772956 (Open Web Text)

Max Activating Token Index: 110

Text #17

Max Range: 3.5911. Min Range: -3.5911

Max Act: 3.5119. Min Act: -0.1700

Data Index: 835595 (Open Web Text)

Max Activating Token Index: 197

Text #18

Max Range: 3.5911. Min Range: -3.5911

Max Act: 3.4632. Min Act: -0.1700

Data Index: 402782 (Open Web Text)

Max Activating Token Index: 274

Text #19

Max Range: 3.5911. Min Range: -3.5911

Max Act: 3.4831. Min Act: -0.1700

Data Index: 1364907 (Open Web Text)

Max Activating Token Index: 423