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

Dataset: Open Web Text

Neuron 2799 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: 0.9798. Min Range: -0.9798

Max Act: 0.9798. Min Act: -0.1377

Data Index: 2606826 (Open Web Text)

Max Activating Token Index: 560

Text #1

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.9680. Min Act: -0.1420

Data Index: 7104938 (Open Web Text)

Max Activating Token Index: 65

Text #2

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.9555. Min Act: -0.1408

Data Index: 5682083 (Open Web Text)

Max Activating Token Index: 57

Text #3

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.9623. Min Act: -0.1424

Data Index: 855403 (Open Web Text)

Max Activating Token Index: 636

Text #4

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.9495. Min Act: -0.1386

Data Index: 563415 (Open Web Text)

Max Activating Token Index: 22

Text #5

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.9461. Min Act: -0.1480

Data Index: 7545908 (Open Web Text)

Max Activating Token Index: 685

Text #6

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.9390. Min Act: -0.1586

Data Index: 2890259 (Open Web Text)

Max Activating Token Index: 50

Text #7

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.9331. Min Act: -0.1522

Data Index: 3784399 (Open Web Text)

Max Activating Token Index: 27

Text #8

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.9371. Min Act: -0.1271

Data Index: 8467351 (Open Web Text)

Max Activating Token Index: 83

Text #9

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.9374. Min Act: -0.1605

Data Index: 6592055 (Open Web Text)

Max Activating Token Index: 878

Text #10

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.9439. Min Act: -0.1656

Data Index: 4902846 (Open Web Text)

Max Activating Token Index: 707

Text #11

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.9325. Min Act: -0.1265

Data Index: 359336 (Open Web Text)

Max Activating Token Index: 878

Text #12

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.9332. Min Act: -0.1329

Data Index: 6934780 (Open Web Text)

Max Activating Token Index: 62

Text #13

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.9343. Min Act: -0.1369

Data Index: 1125750 (Open Web Text)

Max Activating Token Index: 63

Text #14

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.9277. Min Act: -0.1540

Data Index: 6357760 (Open Web Text)

Max Activating Token Index: 60

Text #15

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.9259. Min Act: -0.1658

Data Index: 1355852 (Open Web Text)

Max Activating Token Index: 134

Text #16

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.9253. Min Act: -0.1492

Data Index: 4187221 (Open Web Text)

Max Activating Token Index: 71

Text #17

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.9318. Min Act: -0.1159

Data Index: 6711425 (Open Web Text)

Max Activating Token Index: 51

Text #18

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.9227. Min Act: -0.1578

Data Index: 7672772 (Open Web Text)

Max Activating Token Index: 90

Text #19

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.9188. Min Act: -0.1655

Data Index: 3571517 (Open Web Text)

Max Activating Token Index: 672