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

Dataset: Open Web Text

Neuron 1613 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: 4.5184. Min Range: -4.5184

Max Act: 4.5102. Min Act: -0.1700

Data Index: 3680136 (Open Web Text)

Max Activating Token Index: 389

Text #1

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.5184. Min Act: -0.1700

Data Index: 5065282 (Open Web Text)

Max Activating Token Index: 468

Text #2

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.4920. Min Act: -0.1700

Data Index: 1491470 (Open Web Text)

Max Activating Token Index: 153

Text #3

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.4928. Min Act: -0.1700

Data Index: 249169 (Open Web Text)

Max Activating Token Index: 628

Text #4

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.4671. Min Act: -0.1700

Data Index: 3810652 (Open Web Text)

Max Activating Token Index: 459

Text #5

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.4767. Min Act: -0.1700

Data Index: 394422 (Open Web Text)

Max Activating Token Index: 367

Text #6

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.4375. Min Act: -0.1700

Data Index: 1699527 (Open Web Text)

Max Activating Token Index: 883

Text #7

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.4723. Min Act: -0.1700

Data Index: 4936664 (Open Web Text)

Max Activating Token Index: 560

Text #8

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.4714. Min Act: -0.1700

Data Index: 4264881 (Open Web Text)

Max Activating Token Index: 672

Text #9

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.4625. Min Act: -0.1700

Data Index: 1131035 (Open Web Text)

Max Activating Token Index: 702

Text #10

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.4590. Min Act: -0.1700

Data Index: 814369 (Open Web Text)

Max Activating Token Index: 246

Text #11

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.4450. Min Act: -0.1700

Data Index: 2522577 (Open Web Text)

Max Activating Token Index: 752

Text #12

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.4773. Min Act: -0.1700

Data Index: 8038482 (Open Web Text)

Max Activating Token Index: 376

Text #13

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.4318. Min Act: -0.1700

Data Index: 3766303 (Open Web Text)

Max Activating Token Index: 109

Text #14

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.4452. Min Act: -0.1700

Data Index: 4228216 (Open Web Text)

Max Activating Token Index: 685

Text #15

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.4387. Min Act: -0.1700

Data Index: 4235729 (Open Web Text)

Max Activating Token Index: 346

Text #16

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.4462. Min Act: -0.1700

Data Index: 3252506 (Open Web Text)

Max Activating Token Index: 598

Text #17

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.4120. Min Act: -0.1700

Data Index: 2852478 (Open Web Text)

Max Activating Token Index: 206

Text #18

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.4286. Min Act: -0.1700

Data Index: 4632785 (Open Web Text)

Max Activating Token Index: 594

Text #19

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.4227. Min Act: -0.1700

Data Index: 2762219 (Open Web Text)

Max Activating Token Index: 596