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

Dataset: Open Web Text

Neuron 2082 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: 0.8889. Min Range: -0.8889

Max Act: 0.8889. Min Act: -0.1304

Data Index: 4774748 (Open Web Text)

Max Activating Token Index: 1002

Text #1

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.8533. Min Act: -0.1511

Data Index: 8088784 (Open Web Text)

Max Activating Token Index: 762

Text #2

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.8523. Min Act: -0.1550

Data Index: 4466635 (Open Web Text)

Max Activating Token Index: 38

Text #3

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.8489. Min Act: -0.1161

Data Index: 6355167 (Open Web Text)

Max Activating Token Index: 28

Text #4

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.8391. Min Act: -0.1179

Data Index: 5340867 (Open Web Text)

Max Activating Token Index: 81

Text #5

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.8340. Min Act: -0.1603

Data Index: 7024111 (Open Web Text)

Max Activating Token Index: 1008

Text #6

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.8350. Min Act: -0.1379

Data Index: 3384 (Open Web Text)

Max Activating Token Index: 285

Text #7

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.8330. Min Act: -0.1368

Data Index: 8281616 (Open Web Text)

Max Activating Token Index: 15

Text #8

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.8201. Min Act: -0.1478

Data Index: 6829148 (Open Web Text)

Max Activating Token Index: 36

Text #9

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.8260. Min Act: -0.1536

Data Index: 6792626 (Open Web Text)

Max Activating Token Index: 327

Text #10

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.8246. Min Act: -0.1475

Data Index: 2934725 (Open Web Text)

Max Activating Token Index: 365

Text #11

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.8320. Min Act: -0.1421

Data Index: 7258620 (Open Web Text)

Max Activating Token Index: 34

Text #12

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.8159. Min Act: -0.1256

Data Index: 8634765 (Open Web Text)

Max Activating Token Index: 1017

Text #13

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.8154. Min Act: -0.1091

Data Index: 2147372 (Open Web Text)

Max Activating Token Index: 1018

Text #14

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.8214. Min Act: -0.1149

Data Index: 5720864 (Open Web Text)

Max Activating Token Index: 429

Text #15

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.8163. Min Act: -0.1358

Data Index: 6490593 (Open Web Text)

Max Activating Token Index: 231

Text #16

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.8136. Min Act: -0.1379

Data Index: 3517645 (Open Web Text)

Max Activating Token Index: 246

Text #17

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.8097. Min Act: -0.1098

Data Index: 2604686 (Open Web Text)

Max Activating Token Index: 1021

Text #18

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.8204. Min Act: -0.1294

Data Index: 6444129 (Open Web Text)

Max Activating Token Index: 443

Text #19

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.8077. Min Act: -0.1129

Data Index: 4235271 (Open Web Text)

Max Activating Token Index: 298