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

Dataset: Open Web Text

Neuron 2107 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: 3.7351. Min Range: -3.7351

Max Act: 3.7351. Min Act: -0.1700

Data Index: 1124467 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.7351. Min Range: -3.7351

Max Act: 3.7179. Min Act: -0.1700

Data Index: 6407275 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.7351. Min Range: -3.7351

Max Act: 3.6758. Min Act: -0.1700

Data Index: 542471 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.7351. Min Range: -3.7351

Max Act: 3.6102. Min Act: -0.1700

Data Index: 1990463 (Open Web Text)

Max Activating Token Index: 707

Text #4

Max Range: 3.7351. Min Range: -3.7351

Max Act: 3.5980. Min Act: -0.1700

Data Index: 2685761 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.7351. Min Range: -3.7351

Max Act: 3.5534. Min Act: -0.1700

Data Index: 8466854 (Open Web Text)

Max Activating Token Index: 436

Text #6

Max Range: 3.7351. Min Range: -3.7351

Max Act: 3.5537. Min Act: -0.1700

Data Index: 7081602 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 3.7351. Min Range: -3.7351

Max Act: 3.5700. Min Act: -0.1700

Data Index: 1812741 (Open Web Text)

Max Activating Token Index: 447

Text #8

Max Range: 3.7351. Min Range: -3.7351

Max Act: 3.5788. Min Act: -0.1700

Data Index: 857843 (Open Web Text)

Max Activating Token Index: 398

Text #9

Max Range: 3.7351. Min Range: -3.7351

Max Act: 3.5479. Min Act: -0.1700

Data Index: 7036506 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 3.7351. Min Range: -3.7351

Max Act: 3.5452. Min Act: -0.1700

Data Index: 5633773 (Open Web Text)

Max Activating Token Index: 485

Text #11

Max Range: 3.7351. Min Range: -3.7351

Max Act: 3.5524. Min Act: -0.1700

Data Index: 1892684 (Open Web Text)

Max Activating Token Index: 225

Text #12

Max Range: 3.7351. Min Range: -3.7351

Max Act: 3.5598. Min Act: -0.1700

Data Index: 8173786 (Open Web Text)

Max Activating Token Index: 130

Text #13

Max Range: 3.7351. Min Range: -3.7351

Max Act: 3.5538. Min Act: -0.1700

Data Index: 1676704 (Open Web Text)

Max Activating Token Index: 460

Text #14

Max Range: 3.7351. Min Range: -3.7351

Max Act: 3.5595. Min Act: -0.1700

Data Index: 4571332 (Open Web Text)

Max Activating Token Index: 24

Text #15

Max Range: 3.7351. Min Range: -3.7351

Max Act: 3.5332. Min Act: -0.1700

Data Index: 3727516 (Open Web Text)

Max Activating Token Index: 344

Text #16

Max Range: 3.7351. Min Range: -3.7351

Max Act: 3.5542. Min Act: -0.1700

Data Index: 5740776 (Open Web Text)

Max Activating Token Index: 14

Text #17

Max Range: 3.7351. Min Range: -3.7351

Max Act: 3.5351. Min Act: -0.1700

Data Index: 2886317 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 3.7351. Min Range: -3.7351

Max Act: 3.5097. Min Act: -0.1700

Data Index: 4495920 (Open Web Text)

Max Activating Token Index: 498

Text #19

Max Range: 3.7351. Min Range: -3.7351

Max Act: 3.5302. Min Act: -0.1700

Data Index: 3565894 (Open Web Text)

Max Activating Token Index: 69