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

Dataset: Open Web Text

Neuron 2223 in Layer 6

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: 4.5471. Min Range: -4.5471

Max Act: 4.5471. Min Act: -0.1700

Data Index: 6578349 (Open Web Text)

Max Activating Token Index: 629

Text #1

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.3448. Min Act: -0.1700

Data Index: 4732403 (Open Web Text)

Max Activating Token Index: 307

Text #2

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.3466. Min Act: -0.1700

Data Index: 6652750 (Open Web Text)

Max Activating Token Index: 138

Text #3

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.3203. Min Act: -0.1700

Data Index: 6011205 (Open Web Text)

Max Activating Token Index: 162

Text #4

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.2490. Min Act: -0.1700

Data Index: 8645505 (Open Web Text)

Max Activating Token Index: 221

Text #5

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.2359. Min Act: -0.1700

Data Index: 3610749 (Open Web Text)

Max Activating Token Index: 702

Text #6

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.2091. Min Act: -0.1700

Data Index: 6670776 (Open Web Text)

Max Activating Token Index: 396

Text #7

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.2283. Min Act: -0.1700

Data Index: 3447243 (Open Web Text)

Max Activating Token Index: 88

Text #8

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.1588. Min Act: -0.1700

Data Index: 536105 (Open Web Text)

Max Activating Token Index: 32

Text #9

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.1760. Min Act: -0.1700

Data Index: 5031814 (Open Web Text)

Max Activating Token Index: 880

Text #10

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.2142. Min Act: -0.1700

Data Index: 8517494 (Open Web Text)

Max Activating Token Index: 302

Text #11

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.1899. Min Act: -0.1700

Data Index: 3557156 (Open Web Text)

Max Activating Token Index: 224

Text #12

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.1930. Min Act: -0.1700

Data Index: 2586638 (Open Web Text)

Max Activating Token Index: 301

Text #13

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.1343. Min Act: -0.1700

Data Index: 6309439 (Open Web Text)

Max Activating Token Index: 1012

Text #14

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.1393. Min Act: -0.1700

Data Index: 5103491 (Open Web Text)

Max Activating Token Index: 323

Text #15

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.1511. Min Act: -0.1700

Data Index: 7167301 (Open Web Text)

Max Activating Token Index: 785

Text #16

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.1370. Min Act: -0.1700

Data Index: 1630378 (Open Web Text)

Max Activating Token Index: 358

Text #17

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.1199. Min Act: -0.1700

Data Index: 6973182 (Open Web Text)

Max Activating Token Index: 611

Text #18

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.1410. Min Act: -0.1700

Data Index: 4319671 (Open Web Text)

Max Activating Token Index: 485

Text #19

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.0875. Min Act: -0.1700

Data Index: 4921285 (Open Web Text)

Max Activating Token Index: 302