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

Dataset: Open Web Text

Neuron 1347 in Layer 0

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: 1.1811. Min Range: -1.1811

Max Act: 1.1806. Min Act: -0.1655

Data Index: 5128481 (Open Web Text)

Max Activating Token Index: 625

Text #1

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.1811. Min Act: -0.1655

Data Index: 2847192 (Open Web Text)

Max Activating Token Index: 303

Text #2

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.1699. Min Act: -0.1655

Data Index: 3925498 (Open Web Text)

Max Activating Token Index: 232

Text #3

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.1623. Min Act: -0.1655

Data Index: 2763231 (Open Web Text)

Max Activating Token Index: 247

Text #4

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.1644. Min Act: -0.1655

Data Index: 6063043 (Open Web Text)

Max Activating Token Index: 90

Text #5

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.1552. Min Act: -0.1655

Data Index: 8621825 (Open Web Text)

Max Activating Token Index: 351

Text #6

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.1549. Min Act: -0.1655

Data Index: 3595643 (Open Web Text)

Max Activating Token Index: 563

Text #7

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.1553. Min Act: -0.1655

Data Index: 3928484 (Open Web Text)

Max Activating Token Index: 774

Text #8

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.1530. Min Act: -0.1655

Data Index: 8549060 (Open Web Text)

Max Activating Token Index: 245

Text #9

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.1540. Min Act: -0.1655

Data Index: 1777441 (Open Web Text)

Max Activating Token Index: 167

Text #10

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.1613. Min Act: -0.1655

Data Index: 7167081 (Open Web Text)

Max Activating Token Index: 720

Text #11

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.1433. Min Act: -0.1655

Data Index: 2894580 (Open Web Text)

Max Activating Token Index: 104

Text #12

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.1502. Min Act: -0.1655

Data Index: 7081063 (Open Web Text)

Max Activating Token Index: 740

Text #13

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.1524. Min Act: -0.1655

Data Index: 2793901 (Open Web Text)

Max Activating Token Index: 296

Text #14

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.1490. Min Act: -0.1655

Data Index: 1468561 (Open Web Text)

Max Activating Token Index: 169

Text #15

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.1407. Min Act: -0.1655

Data Index: 2757051 (Open Web Text)

Max Activating Token Index: 488

Text #16

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.1549. Min Act: -0.1655

Data Index: 2030459 (Open Web Text)

Max Activating Token Index: 962

Text #17

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.1378. Min Act: -0.1655

Data Index: 4052891 (Open Web Text)

Max Activating Token Index: 706

Text #18

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.1429. Min Act: -0.1655

Data Index: 1534948 (Open Web Text)

Max Activating Token Index: 975

Text #19

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.1430. Min Act: -0.1655

Data Index: 5518613 (Open Web Text)

Max Activating Token Index: 202