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

Dataset: Open Web Text

Neuron 1430 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: 4.0180. Min Range: -4.0180

Max Act: 4.0180. Min Act: -0.1700

Data Index: 3109503 (Open Web Text)

Max Activating Token Index: 310

Text #1

Max Range: 4.0180. Min Range: -4.0180

Max Act: 4.0032. Min Act: -0.1700

Data Index: 4860481 (Open Web Text)

Max Activating Token Index: 367

Text #2

Max Range: 4.0180. Min Range: -4.0180

Max Act: 3.9623. Min Act: -0.1700

Data Index: 6373673 (Open Web Text)

Max Activating Token Index: 468

Text #3

Max Range: 4.0180. Min Range: -4.0180

Max Act: 3.9709. Min Act: -0.1700

Data Index: 3254530 (Open Web Text)

Max Activating Token Index: 247

Text #4

Max Range: 4.0180. Min Range: -4.0180

Max Act: 3.9387. Min Act: -0.1700

Data Index: 7538221 (Open Web Text)

Max Activating Token Index: 370

Text #5

Max Range: 4.0180. Min Range: -4.0180

Max Act: 3.9601. Min Act: -0.1700

Data Index: 7732602 (Open Web Text)

Max Activating Token Index: 207

Text #6

Max Range: 4.0180. Min Range: -4.0180

Max Act: 3.9397. Min Act: -0.1700

Data Index: 5710359 (Open Web Text)

Max Activating Token Index: 508

Text #7

Max Range: 4.0180. Min Range: -4.0180

Max Act: 3.9272. Min Act: -0.1700

Data Index: 1494590 (Open Web Text)

Max Activating Token Index: 475

Text #8

Max Range: 4.0180. Min Range: -4.0180

Max Act: 3.9416. Min Act: -0.1700

Data Index: 3568 (Open Web Text)

Max Activating Token Index: 574

Text #9

Max Range: 4.0180. Min Range: -4.0180

Max Act: 3.9275. Min Act: -0.1700

Data Index: 692910 (Open Web Text)

Max Activating Token Index: 408

Text #10

Max Range: 4.0180. Min Range: -4.0180

Max Act: 3.9052. Min Act: -0.1700

Data Index: 5019035 (Open Web Text)

Max Activating Token Index: 512

Text #11

Max Range: 4.0180. Min Range: -4.0180

Max Act: 3.8986. Min Act: -0.1700

Data Index: 4801612 (Open Web Text)

Max Activating Token Index: 408

Text #12

Max Range: 4.0180. Min Range: -4.0180

Max Act: 3.9305. Min Act: -0.1700

Data Index: 2061972 (Open Web Text)

Max Activating Token Index: 563

Text #13

Max Range: 4.0180. Min Range: -4.0180

Max Act: 3.9216. Min Act: -0.1700

Data Index: 4456177 (Open Web Text)

Max Activating Token Index: 439

Text #14

Max Range: 4.0180. Min Range: -4.0180

Max Act: 3.8959. Min Act: -0.1700

Data Index: 4285900 (Open Web Text)

Max Activating Token Index: 344

Text #15

Max Range: 4.0180. Min Range: -4.0180

Max Act: 3.9133. Min Act: -0.1700

Data Index: 4222693 (Open Web Text)

Max Activating Token Index: 489

Text #16

Max Range: 4.0180. Min Range: -4.0180

Max Act: 3.9006. Min Act: -0.1700

Data Index: 3578741 (Open Web Text)

Max Activating Token Index: 466

Text #17

Max Range: 4.0180. Min Range: -4.0180

Max Act: 3.9011. Min Act: -0.1700

Data Index: 2891064 (Open Web Text)

Max Activating Token Index: 797

Text #18

Max Range: 4.0180. Min Range: -4.0180

Max Act: 3.9087. Min Act: -0.1700

Data Index: 2626902 (Open Web Text)

Max Activating Token Index: 407

Text #19

Max Range: 4.0180. Min Range: -4.0180

Max Act: 3.9250. Min Act: -0.1700

Data Index: 2554077 (Open Web Text)

Max Activating Token Index: 309