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

Dataset: Open Web Text

Neuron 1322 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: 1.4901. Min Range: -1.4901

Max Act: 1.4901. Min Act: -0.1700

Data Index: 1901427 (Open Web Text)

Max Activating Token Index: 328

Text #1

Max Range: 1.4901. Min Range: -1.4901

Max Act: 1.4447. Min Act: -0.1700

Data Index: 130328 (Open Web Text)

Max Activating Token Index: 323

Text #2

Max Range: 1.4901. Min Range: -1.4901

Max Act: 1.4380. Min Act: -0.1700

Data Index: 2272199 (Open Web Text)

Max Activating Token Index: 328

Text #3

Max Range: 1.4901. Min Range: -1.4901

Max Act: 1.4514. Min Act: -0.1700

Data Index: 8718349 (Open Web Text)

Max Activating Token Index: 309

Text #4

Max Range: 1.4901. Min Range: -1.4901

Max Act: 1.4430. Min Act: -0.1700

Data Index: 24074 (Open Web Text)

Max Activating Token Index: 320

Text #5

Max Range: 1.4901. Min Range: -1.4901

Max Act: 1.4469. Min Act: -0.1700

Data Index: 130332 (Open Web Text)

Max Activating Token Index: 323

Text #6

Max Range: 1.4901. Min Range: -1.4901

Max Act: 1.4178. Min Act: -0.1700

Data Index: 2221551 (Open Web Text)

Max Activating Token Index: 332

Text #7

Max Range: 1.4901. Min Range: -1.4901

Max Act: 1.4255. Min Act: -0.1700

Data Index: 5840513 (Open Web Text)

Max Activating Token Index: 325

Text #8

Max Range: 1.4901. Min Range: -1.4901

Max Act: 1.4181. Min Act: -0.1700

Data Index: 8718362 (Open Web Text)

Max Activating Token Index: 327

Text #9

Max Range: 1.4901. Min Range: -1.4901

Max Act: 1.4214. Min Act: -0.1700

Data Index: 2221562 (Open Web Text)

Max Activating Token Index: 323

Text #10

Max Range: 1.4901. Min Range: -1.4901

Max Act: 1.4351. Min Act: -0.1700

Data Index: 4023802 (Open Web Text)

Max Activating Token Index: 334

Text #11

Max Range: 1.4901. Min Range: -1.4901

Max Act: 1.4237. Min Act: -0.1700

Data Index: 4996948 (Open Web Text)

Max Activating Token Index: 328

Text #12

Max Range: 1.4901. Min Range: -1.4901

Max Act: 1.4089. Min Act: -0.1700

Data Index: 2677977 (Open Web Text)

Max Activating Token Index: 325

Text #13

Max Range: 1.4901. Min Range: -1.4901

Max Act: 1.4121. Min Act: -0.1700

Data Index: 2677979 (Open Web Text)

Max Activating Token Index: 333

Text #14

Max Range: 1.4901. Min Range: -1.4901

Max Act: 1.4031. Min Act: -0.1700

Data Index: 1274269 (Open Web Text)

Max Activating Token Index: 313

Text #15

Max Range: 1.4901. Min Range: -1.4901

Max Act: 1.4093. Min Act: -0.1700

Data Index: 2976049 (Open Web Text)

Max Activating Token Index: 323

Text #16

Max Range: 1.4901. Min Range: -1.4901

Max Act: 1.4122. Min Act: -0.1700

Data Index: 1482481 (Open Web Text)

Max Activating Token Index: 316

Text #17

Max Range: 1.4901. Min Range: -1.4901

Max Act: 1.4034. Min Act: -0.1700

Data Index: 4649022 (Open Web Text)

Max Activating Token Index: 317

Text #18

Max Range: 1.4901. Min Range: -1.4901

Max Act: 1.4091. Min Act: -0.1700

Data Index: 4819378 (Open Web Text)

Max Activating Token Index: 322

Text #19

Max Range: 1.4901. Min Range: -1.4901

Max Act: 1.4085. Min Act: -0.1700

Data Index: 1799289 (Open Web Text)

Max Activating Token Index: 330