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

Dataset: Open Web Text

Neuron 1215 in Layer 5

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: 3.3822. Min Range: -3.3822

Max Act: 3.3822. Min Act: -0.1700

Data Index: 1506574 (Open Web Text)

Max Activating Token Index: 418

Text #1

Max Range: 3.3822. Min Range: -3.3822

Max Act: 3.3757. Min Act: -0.1700

Data Index: 333362 (Open Web Text)

Max Activating Token Index: 427

Text #2

Max Range: 3.3822. Min Range: -3.3822

Max Act: 3.3004. Min Act: -0.1700

Data Index: 7000130 (Open Web Text)

Max Activating Token Index: 977

Text #3

Max Range: 3.3822. Min Range: -3.3822

Max Act: 3.2608. Min Act: -0.1700

Data Index: 420739 (Open Web Text)

Max Activating Token Index: 830

Text #4

Max Range: 3.3822. Min Range: -3.3822

Max Act: 3.2636. Min Act: -0.1700

Data Index: 5738579 (Open Web Text)

Max Activating Token Index: 873

Text #5

Max Range: 3.3822. Min Range: -3.3822

Max Act: 3.2518. Min Act: -0.1700

Data Index: 1802986 (Open Web Text)

Max Activating Token Index: 70

Text #6

Max Range: 3.3822. Min Range: -3.3822

Max Act: 3.2496. Min Act: -0.1700

Data Index: 1221363 (Open Web Text)

Max Activating Token Index: 390

Text #7

Max Range: 3.3822. Min Range: -3.3822

Max Act: 3.2258. Min Act: -0.1700

Data Index: 8240273 (Open Web Text)

Max Activating Token Index: 332

Text #8

Max Range: 3.3822. Min Range: -3.3822

Max Act: 3.1911. Min Act: -0.1700

Data Index: 1768990 (Open Web Text)

Max Activating Token Index: 41

Text #9

Max Range: 3.3822. Min Range: -3.3822

Max Act: 3.1815. Min Act: -0.1700

Data Index: 1477764 (Open Web Text)

Max Activating Token Index: 572

Text #10

Max Range: 3.3822. Min Range: -3.3822

Max Act: 3.1747. Min Act: -0.1700

Data Index: 1029324 (Open Web Text)

Max Activating Token Index: 940

Text #11

Max Range: 3.3822. Min Range: -3.3822

Max Act: 3.1556. Min Act: -0.1700

Data Index: 694255 (Open Web Text)

Max Activating Token Index: 884

Text #12

Max Range: 3.3822. Min Range: -3.3822

Max Act: 3.1872. Min Act: -0.1700

Data Index: 463962 (Open Web Text)

Max Activating Token Index: 361

Text #13

Max Range: 3.3822. Min Range: -3.3822

Max Act: 3.1607. Min Act: -0.1700

Data Index: 7455117 (Open Web Text)

Max Activating Token Index: 380

Text #14

Max Range: 3.3822. Min Range: -3.3822

Max Act: 3.1800. Min Act: -0.1700

Data Index: 8271339 (Open Web Text)

Max Activating Token Index: 24

Text #15

Max Range: 3.3822. Min Range: -3.3822

Max Act: 3.1721. Min Act: -0.1700

Data Index: 899941 (Open Web Text)

Max Activating Token Index: 309

Text #16

Max Range: 3.3822. Min Range: -3.3822

Max Act: 3.1470. Min Act: -0.1700

Data Index: 6272654 (Open Web Text)

Max Activating Token Index: 708

Text #17

Max Range: 3.3822. Min Range: -3.3822

Max Act: 3.1321. Min Act: -0.1700

Data Index: 3718448 (Open Web Text)

Max Activating Token Index: 460

Text #18

Max Range: 3.3822. Min Range: -3.3822

Max Act: 3.1344. Min Act: -0.1700

Data Index: 3854350 (Open Web Text)

Max Activating Token Index: 198

Text #19

Max Range: 3.3822. Min Range: -3.3822

Max Act: 3.1272. Min Act: -0.1700

Data Index: 5054044 (Open Web Text)

Max Activating Token Index: 188