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

Dataset: Open Web Text

Neuron 37 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: -0.0429. Min Range: 0.0429

Max Act: -0.0429. Min Act: -0.1700

Data Index: 4186479 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: -0.0429. Min Range: 0.0429

Max Act: -0.0442. Min Act: -0.1700

Data Index: 6611703 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: -0.0429. Min Range: 0.0429

Max Act: -0.0451. Min Act: -0.1700

Data Index: 7394505 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: -0.0429. Min Range: 0.0429

Max Act: -0.0458. Min Act: -0.1700

Data Index: 6021625 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: -0.0429. Min Range: 0.0429

Max Act: -0.0457. Min Act: -0.1700

Data Index: 1541697 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: -0.0429. Min Range: 0.0429

Max Act: -0.0449. Min Act: -0.1700

Data Index: 6663774 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: -0.0429. Min Range: 0.0429

Max Act: -0.0478. Min Act: -0.1700

Data Index: 5280717 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: -0.0429. Min Range: 0.0429

Max Act: -0.0480. Min Act: -0.1700

Data Index: 3895652 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: -0.0429. Min Range: 0.0429

Max Act: -0.0471. Min Act: -0.1700

Data Index: 8703244 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: -0.0429. Min Range: 0.0429

Max Act: -0.0477. Min Act: -0.1700

Data Index: 7864071 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: -0.0429. Min Range: 0.0429

Max Act: -0.0479. Min Act: -0.1700

Data Index: 7719932 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: -0.0429. Min Range: 0.0429

Max Act: -0.0484. Min Act: -0.1700

Data Index: 7691017 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: -0.0429. Min Range: 0.0429

Max Act: -0.0484. Min Act: -0.1700

Data Index: 7398512 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: -0.0429. Min Range: 0.0429

Max Act: -0.0465. Min Act: -0.1695

Data Index: 998460 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: -0.0429. Min Range: 0.0429

Max Act: -0.0475. Min Act: -0.1700

Data Index: 7271312 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: -0.0429. Min Range: 0.0429

Max Act: -0.0463. Min Act: -0.1700

Data Index: 6944681 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: -0.0429. Min Range: 0.0429

Max Act: -0.0475. Min Act: -0.1700

Data Index: 2864436 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: -0.0429. Min Range: 0.0429

Max Act: -0.0476. Min Act: -0.1700

Data Index: 6273416 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: -0.0429. Min Range: 0.0429

Max Act: -0.0470. Min Act: -0.1666

Data Index: 6111876 (Open Web Text)

Max Activating Token Index: 1020

Text #19

Max Range: -0.0429. Min Range: 0.0429

Max Act: -0.0489. Min Act: -0.1700

Data Index: 2253860 (Open Web Text)

Max Activating Token Index: 2