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

Dataset: Open Web Text

Neuron 2506 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: 3.2047. Min Range: -3.2047

Max Act: 3.2047. Min Act: -0.1700

Data Index: 7171015 (Open Web Text)

Max Activating Token Index: 164

Text #1

Max Range: 3.2047. Min Range: -3.2047

Max Act: 3.1993. Min Act: -0.1700

Data Index: 7526490 (Open Web Text)

Max Activating Token Index: 466

Text #2

Max Range: 3.2047. Min Range: -3.2047

Max Act: 3.1907. Min Act: -0.1700

Data Index: 1128784 (Open Web Text)

Max Activating Token Index: 501

Text #3

Max Range: 3.2047. Min Range: -3.2047

Max Act: 3.1691. Min Act: -0.1700

Data Index: 5159042 (Open Web Text)

Max Activating Token Index: 510

Text #4

Max Range: 3.2047. Min Range: -3.2047

Max Act: 3.1827. Min Act: -0.1700

Data Index: 278747 (Open Web Text)

Max Activating Token Index: 241

Text #5

Max Range: 3.2047. Min Range: -3.2047

Max Act: 3.1778. Min Act: -0.1700

Data Index: 520497 (Open Web Text)

Max Activating Token Index: 108

Text #6

Max Range: 3.2047. Min Range: -3.2047

Max Act: 3.1615. Min Act: -0.1700

Data Index: 1421684 (Open Web Text)

Max Activating Token Index: 187

Text #7

Max Range: 3.2047. Min Range: -3.2047

Max Act: 3.1696. Min Act: -0.1700

Data Index: 2350522 (Open Web Text)

Max Activating Token Index: 545

Text #8

Max Range: 3.2047. Min Range: -3.2047

Max Act: 3.1527. Min Act: -0.1700

Data Index: 1831186 (Open Web Text)

Max Activating Token Index: 555

Text #9

Max Range: 3.2047. Min Range: -3.2047

Max Act: 3.1636. Min Act: -0.1700

Data Index: 1740310 (Open Web Text)

Max Activating Token Index: 497

Text #10

Max Range: 3.2047. Min Range: -3.2047

Max Act: 3.1633. Min Act: -0.1700

Data Index: 5920287 (Open Web Text)

Max Activating Token Index: 138

Text #11

Max Range: 3.2047. Min Range: -3.2047

Max Act: 3.1583. Min Act: -0.1700

Data Index: 4911685 (Open Web Text)

Max Activating Token Index: 172

Text #12

Max Range: 3.2047. Min Range: -3.2047

Max Act: 3.1717. Min Act: -0.1700

Data Index: 135648 (Open Web Text)

Max Activating Token Index: 126

Text #13

Max Range: 3.2047. Min Range: -3.2047

Max Act: 3.1687. Min Act: -0.1700

Data Index: 2798341 (Open Web Text)

Max Activating Token Index: 467

Text #14

Max Range: 3.2047. Min Range: -3.2047

Max Act: 3.1541. Min Act: -0.1700

Data Index: 6955695 (Open Web Text)

Max Activating Token Index: 277

Text #15

Max Range: 3.2047. Min Range: -3.2047

Max Act: 3.1658. Min Act: -0.1700

Data Index: 4233459 (Open Web Text)

Max Activating Token Index: 375

Text #16

Max Range: 3.2047. Min Range: -3.2047

Max Act: 3.1389. Min Act: -0.1700

Data Index: 347473 (Open Web Text)

Max Activating Token Index: 477

Text #17

Max Range: 3.2047. Min Range: -3.2047

Max Act: 3.1347. Min Act: -0.1700

Data Index: 4530954 (Open Web Text)

Max Activating Token Index: 363

Text #18

Max Range: 3.2047. Min Range: -3.2047

Max Act: 3.1393. Min Act: -0.1700

Data Index: 3355193 (Open Web Text)

Max Activating Token Index: 418

Text #19

Max Range: 3.2047. Min Range: -3.2047

Max Act: 3.1320. Min Act: -0.1700

Data Index: 3430315 (Open Web Text)

Max Activating Token Index: 347