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

Dataset: Open Web Text

Neuron 690 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: 1.8666. Min Range: -1.8666

Max Act: 1.8662. Min Act: -0.1700

Data Index: 2484660 (Open Web Text)

Max Activating Token Index: 559

Text #1

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.8666. Min Act: -0.1700

Data Index: 247801 (Open Web Text)

Max Activating Token Index: 142

Text #2

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.8608. Min Act: -0.1700

Data Index: 4467214 (Open Web Text)

Max Activating Token Index: 707

Text #3

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.8410. Min Act: -0.1700

Data Index: 3676793 (Open Web Text)

Max Activating Token Index: 228

Text #4

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.8246. Min Act: -0.1700

Data Index: 8095425 (Open Web Text)

Max Activating Token Index: 232

Text #5

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.8223. Min Act: -0.1700

Data Index: 5793867 (Open Web Text)

Max Activating Token Index: 315

Text #6

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.8334. Min Act: -0.1699

Data Index: 7698965 (Open Web Text)

Max Activating Token Index: 225

Text #7

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.8269. Min Act: -0.1700

Data Index: 635314 (Open Web Text)

Max Activating Token Index: 283

Text #8

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.8270. Min Act: -0.1700

Data Index: 6167119 (Open Web Text)

Max Activating Token Index: 437

Text #9

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.8202. Min Act: -0.1700

Data Index: 2795034 (Open Web Text)

Max Activating Token Index: 809

Text #10

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.8166. Min Act: -0.1700

Data Index: 3272873 (Open Web Text)

Max Activating Token Index: 897

Text #11

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.8204. Min Act: -0.1700

Data Index: 1986949 (Open Web Text)

Max Activating Token Index: 290

Text #12

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.7930. Min Act: -0.1700

Data Index: 5340678 (Open Web Text)

Max Activating Token Index: 819

Text #13

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.8015. Min Act: -0.1700

Data Index: 1979923 (Open Web Text)

Max Activating Token Index: 686

Text #14

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.7922. Min Act: -0.1700

Data Index: 4654339 (Open Web Text)

Max Activating Token Index: 819

Text #15

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.7995. Min Act: -0.1700

Data Index: 3920944 (Open Web Text)

Max Activating Token Index: 520

Text #16

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.7997. Min Act: -0.1700

Data Index: 4893275 (Open Web Text)

Max Activating Token Index: 25

Text #17

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.7975. Min Act: -0.1700

Data Index: 3218686 (Open Web Text)

Max Activating Token Index: 947

Text #18

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.8029. Min Act: -0.1700

Data Index: 6741449 (Open Web Text)

Max Activating Token Index: 203

Text #19

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.7915. Min Act: -0.1700

Data Index: 1921316 (Open Web Text)

Max Activating Token Index: 253