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

Dataset: Open Web Text

Neuron 1828 in Layer 3

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: 3.3586. Min Range: -3.3586

Max Act: 3.2840. Min Act: -0.1700

Data Index: 3501703 (Open Web Text)

Max Activating Token Index: 909

Text #1

Max Range: 3.3586. Min Range: -3.3586

Max Act: 3.3586. Min Act: -0.1700

Data Index: 6333825 (Open Web Text)

Max Activating Token Index: 1010

Text #2

Max Range: 3.3586. Min Range: -3.3586

Max Act: 3.2132. Min Act: -0.1700

Data Index: 24040 (Open Web Text)

Max Activating Token Index: 630

Text #3

Max Range: 3.3586. Min Range: -3.3586

Max Act: 3.1758. Min Act: -0.1700

Data Index: 6921591 (Open Web Text)

Max Activating Token Index: 320

Text #4

Max Range: 3.3586. Min Range: -3.3586

Max Act: 3.1617. Min Act: -0.1700

Data Index: 4429194 (Open Web Text)

Max Activating Token Index: 699

Text #5

Max Range: 3.3586. Min Range: -3.3586

Max Act: 3.1670. Min Act: -0.1700

Data Index: 2637169 (Open Web Text)

Max Activating Token Index: 61

Text #6

Max Range: 3.3586. Min Range: -3.3586

Max Act: 3.1723. Min Act: -0.1700

Data Index: 6708769 (Open Web Text)

Max Activating Token Index: 247

Text #7

Max Range: 3.3586. Min Range: -3.3586

Max Act: 3.1292. Min Act: -0.1700

Data Index: 7130898 (Open Web Text)

Max Activating Token Index: 624

Text #8

Max Range: 3.3586. Min Range: -3.3586

Max Act: 3.1290. Min Act: -0.1700

Data Index: 4589657 (Open Web Text)

Max Activating Token Index: 336

Text #9

Max Range: 3.3586. Min Range: -3.3586

Max Act: 3.1241. Min Act: -0.1700

Data Index: 4634861 (Open Web Text)

Max Activating Token Index: 487

Text #10

Max Range: 3.3586. Min Range: -3.3586

Max Act: 3.1408. Min Act: -0.1700

Data Index: 5936163 (Open Web Text)

Max Activating Token Index: 986

Text #11

Max Range: 3.3586. Min Range: -3.3586

Max Act: 3.1225. Min Act: -0.1700

Data Index: 3675409 (Open Web Text)

Max Activating Token Index: 444

Text #12

Max Range: 3.3586. Min Range: -3.3586

Max Act: 3.1063. Min Act: -0.1700

Data Index: 3594493 (Open Web Text)

Max Activating Token Index: 281

Text #13

Max Range: 3.3586. Min Range: -3.3586

Max Act: 3.1283. Min Act: -0.1700

Data Index: 1445702 (Open Web Text)

Max Activating Token Index: 543

Text #14

Max Range: 3.3586. Min Range: -3.3586

Max Act: 3.1010. Min Act: -0.1700

Data Index: 4039396 (Open Web Text)

Max Activating Token Index: 847

Text #15

Max Range: 3.3586. Min Range: -3.3586

Max Act: 3.0899. Min Act: -0.1700

Data Index: 4117478 (Open Web Text)

Max Activating Token Index: 463

Text #16

Max Range: 3.3586. Min Range: -3.3586

Max Act: 3.1033. Min Act: -0.1700

Data Index: 1445700 (Open Web Text)

Max Activating Token Index: 702

Text #17

Max Range: 3.3586. Min Range: -3.3586

Max Act: 3.1045. Min Act: -0.1700

Data Index: 2908197 (Open Web Text)

Max Activating Token Index: 801

Text #18

Max Range: 3.3586. Min Range: -3.3586

Max Act: 3.0757. Min Act: -0.1700

Data Index: 7556804 (Open Web Text)

Max Activating Token Index: 149

Text #19

Max Range: 3.3586. Min Range: -3.3586

Max Act: 3.0844. Min Act: -0.1700

Data Index: 1273247 (Open Web Text)

Max Activating Token Index: 405