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

Dataset: Open Web Text

Neuron 0 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: 1.4755. Min Range: -1.4755

Max Act: 1.4755. Min Act: -0.0822

Data Index: 2434749 (Open Web Text)

Max Activating Token Index: 339

Text #1

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.4371. Min Act: -0.0822

Data Index: 5579927 (Open Web Text)

Max Activating Token Index: 349

Text #2

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.4261. Min Act: -0.1163

Data Index: 5579917 (Open Web Text)

Max Activating Token Index: 341

Text #3

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.4335. Min Act: -0.0822

Data Index: 5579919 (Open Web Text)

Max Activating Token Index: 339

Text #4

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.4236. Min Act: -0.0822

Data Index: 5579926 (Open Web Text)

Max Activating Token Index: 324

Text #5

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.4213. Min Act: -0.0822

Data Index: 5579925 (Open Web Text)

Max Activating Token Index: 923

Text #6

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.4264. Min Act: -0.0822

Data Index: 7022503 (Open Web Text)

Max Activating Token Index: 822

Text #7

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.4172. Min Act: -0.1272

Data Index: 5567546 (Open Web Text)

Max Activating Token Index: 184

Text #8

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.4215. Min Act: -0.0822

Data Index: 390408 (Open Web Text)

Max Activating Token Index: 397

Text #9

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.4185. Min Act: -0.0822

Data Index: 3790852 (Open Web Text)

Max Activating Token Index: 595

Text #10

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.4167. Min Act: -0.0822

Data Index: 5579918 (Open Web Text)

Max Activating Token Index: 882

Text #11

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.4115. Min Act: -0.1342

Data Index: 2782080 (Open Web Text)

Max Activating Token Index: 900

Text #12

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.4020. Min Act: -0.1175

Data Index: 7027176 (Open Web Text)

Max Activating Token Index: 79

Text #13

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.4013. Min Act: -0.1610

Data Index: 2311584 (Open Web Text)

Max Activating Token Index: 224

Text #14

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.3959. Min Act: -0.1440

Data Index: 5004147 (Open Web Text)

Max Activating Token Index: 570

Text #15

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.3995. Min Act: -0.0822

Data Index: 7949725 (Open Web Text)

Max Activating Token Index: 326

Text #16

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.3924. Min Act: -0.0822

Data Index: 1844020 (Open Web Text)

Max Activating Token Index: 389

Text #17

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.3921. Min Act: -0.1521

Data Index: 1774035 (Open Web Text)

Max Activating Token Index: 232

Text #18

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.3937. Min Act: -0.0822

Data Index: 5583748 (Open Web Text)

Max Activating Token Index: 980

Text #19

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.3826. Min Act: -0.1410

Data Index: 4815308 (Open Web Text)

Max Activating Token Index: 459