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

Dataset: Open Web Text

Neuron 894 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: 4.0764. Min Range: -4.0764

Max Act: 4.0629. Min Act: -0.1700

Data Index: 2118350 (Open Web Text)

Max Activating Token Index: 338

Text #1

Max Range: 4.0764. Min Range: -4.0764

Max Act: 4.0756. Min Act: -0.1700

Data Index: 2353957 (Open Web Text)

Max Activating Token Index: 333

Text #2

Max Range: 4.0764. Min Range: -4.0764

Max Act: 4.0635. Min Act: -0.1700

Data Index: 8802615 (Open Web Text)

Max Activating Token Index: 338

Text #3

Max Range: 4.0764. Min Range: -4.0764

Max Act: 4.0737. Min Act: -0.1700

Data Index: 3947209 (Open Web Text)

Max Activating Token Index: 561

Text #4

Max Range: 4.0764. Min Range: -4.0764

Max Act: 4.0764. Min Act: -0.1700

Data Index: 3415601 (Open Web Text)

Max Activating Token Index: 565

Text #5

Max Range: 4.0764. Min Range: -4.0764

Max Act: 4.0577. Min Act: -0.1700

Data Index: 4014019 (Open Web Text)

Max Activating Token Index: 270

Text #6

Max Range: 4.0764. Min Range: -4.0764

Max Act: 4.0417. Min Act: -0.1700

Data Index: 348487 (Open Web Text)

Max Activating Token Index: 320

Text #7

Max Range: 4.0764. Min Range: -4.0764

Max Act: 4.0640. Min Act: -0.1700

Data Index: 2356237 (Open Web Text)

Max Activating Token Index: 350

Text #8

Max Range: 4.0764. Min Range: -4.0764

Max Act: 4.0372. Min Act: -0.1700

Data Index: 6942594 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 4.0764. Min Range: -4.0764

Max Act: 4.0293. Min Act: -0.1700

Data Index: 575109 (Open Web Text)

Max Activating Token Index: 330

Text #10

Max Range: 4.0764. Min Range: -4.0764

Max Act: 4.0091. Min Act: -0.1700

Data Index: 3792717 (Open Web Text)

Max Activating Token Index: 449

Text #11

Max Range: 4.0764. Min Range: -4.0764

Max Act: 4.0169. Min Act: -0.1700

Data Index: 1210008 (Open Web Text)

Max Activating Token Index: 158

Text #12

Max Range: 4.0764. Min Range: -4.0764

Max Act: 4.0293. Min Act: -0.1700

Data Index: 3248121 (Open Web Text)

Max Activating Token Index: 521

Text #13

Max Range: 4.0764. Min Range: -4.0764

Max Act: 3.9962. Min Act: -0.1700

Data Index: 1097524 (Open Web Text)

Max Activating Token Index: 368

Text #14

Max Range: 4.0764. Min Range: -4.0764

Max Act: 4.0043. Min Act: -0.1700

Data Index: 1046272 (Open Web Text)

Max Activating Token Index: 302

Text #15

Max Range: 4.0764. Min Range: -4.0764

Max Act: 4.0140. Min Act: -0.1700

Data Index: 84552 (Open Web Text)

Max Activating Token Index: 588

Text #16

Max Range: 4.0764. Min Range: -4.0764

Max Act: 4.0143. Min Act: -0.1700

Data Index: 3143745 (Open Web Text)

Max Activating Token Index: 547

Text #17

Max Range: 4.0764. Min Range: -4.0764

Max Act: 3.9908. Min Act: -0.1700

Data Index: 3116928 (Open Web Text)

Max Activating Token Index: 366

Text #18

Max Range: 4.0764. Min Range: -4.0764

Max Act: 4.0041. Min Act: -0.1700

Data Index: 2915575 (Open Web Text)

Max Activating Token Index: 341

Text #19

Max Range: 4.0764. Min Range: -4.0764

Max Act: 4.0246. Min Act: -0.1700

Data Index: 2904940 (Open Web Text)

Max Activating Token Index: 376