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

Dataset: Open Web Text

Neuron 2364 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: 1.5014. Min Range: -1.5014

Max Act: 1.5014. Min Act: -0.1700

Data Index: 137499 (Open Web Text)

Max Activating Token Index: 296

Text #1

Max Range: 1.5014. Min Range: -1.5014

Max Act: 1.4859. Min Act: -0.1700

Data Index: 3255769 (Open Web Text)

Max Activating Token Index: 315

Text #2

Max Range: 1.5014. Min Range: -1.5014

Max Act: 1.4747. Min Act: -0.1694

Data Index: 4797349 (Open Web Text)

Max Activating Token Index: 296

Text #3

Max Range: 1.5014. Min Range: -1.5014

Max Act: 1.4668. Min Act: -0.1700

Data Index: 4856081 (Open Web Text)

Max Activating Token Index: 78

Text #4

Max Range: 1.5014. Min Range: -1.5014

Max Act: 1.4685. Min Act: -0.1700

Data Index: 3077021 (Open Web Text)

Max Activating Token Index: 235

Text #5

Max Range: 1.5014. Min Range: -1.5014

Max Act: 1.4645. Min Act: -0.1700

Data Index: 7996559 (Open Web Text)

Max Activating Token Index: 419

Text #6

Max Range: 1.5014. Min Range: -1.5014

Max Act: 1.4529. Min Act: -0.1700

Data Index: 2084775 (Open Web Text)

Max Activating Token Index: 336

Text #7

Max Range: 1.5014. Min Range: -1.5014

Max Act: 1.4535. Min Act: -0.1700

Data Index: 3075383 (Open Web Text)

Max Activating Token Index: 359

Text #8

Max Range: 1.5014. Min Range: -1.5014

Max Act: 1.4559. Min Act: -0.1695

Data Index: 6550081 (Open Web Text)

Max Activating Token Index: 382

Text #9

Max Range: 1.5014. Min Range: -1.5014

Max Act: 1.4480. Min Act: -0.1700

Data Index: 4617983 (Open Web Text)

Max Activating Token Index: 306

Text #10

Max Range: 1.5014. Min Range: -1.5014

Max Act: 1.4475. Min Act: -0.1700

Data Index: 5339568 (Open Web Text)

Max Activating Token Index: 238

Text #11

Max Range: 1.5014. Min Range: -1.5014

Max Act: 1.4382. Min Act: -0.1700

Data Index: 1092567 (Open Web Text)

Max Activating Token Index: 266

Text #12

Max Range: 1.5014. Min Range: -1.5014

Max Act: 1.4452. Min Act: -0.1700

Data Index: 5166610 (Open Web Text)

Max Activating Token Index: 267

Text #13

Max Range: 1.5014. Min Range: -1.5014

Max Act: 1.4448. Min Act: -0.1700

Data Index: 7075765 (Open Web Text)

Max Activating Token Index: 330

Text #14

Max Range: 1.5014. Min Range: -1.5014

Max Act: 1.4470. Min Act: -0.1695

Data Index: 4901436 (Open Web Text)

Max Activating Token Index: 436

Text #15

Max Range: 1.5014. Min Range: -1.5014

Max Act: 1.4467. Min Act: -0.1694

Data Index: 1467385 (Open Web Text)

Max Activating Token Index: 360

Text #16

Max Range: 1.5014. Min Range: -1.5014

Max Act: 1.4448. Min Act: -0.1700

Data Index: 4849840 (Open Web Text)

Max Activating Token Index: 934

Text #17

Max Range: 1.5014. Min Range: -1.5014

Max Act: 1.4335. Min Act: -0.1700

Data Index: 3377182 (Open Web Text)

Max Activating Token Index: 258

Text #18

Max Range: 1.5014. Min Range: -1.5014

Max Act: 1.4400. Min Act: -0.1700

Data Index: 3286982 (Open Web Text)

Max Activating Token Index: 447

Text #19

Max Range: 1.5014. Min Range: -1.5014

Max Act: 1.4299. Min Act: -0.1697

Data Index: 1748489 (Open Web Text)

Max Activating Token Index: 332