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

Dataset: Open Web Text

Neuron 2259 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: 4.3076. Min Range: -4.3076

Max Act: 4.3076. Min Act: -0.1700

Data Index: 1254375 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.2961. Min Act: -0.1700

Data Index: 2035933 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.2844. Min Act: -0.1700

Data Index: 1917219 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.2605. Min Act: -0.1700

Data Index: 7592205 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.2683. Min Act: -0.1700

Data Index: 1401545 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.2613. Min Act: -0.1700

Data Index: 7280062 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.2625. Min Act: -0.1700

Data Index: 1388473 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.2710. Min Act: -0.1700

Data Index: 1195922 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.2504. Min Act: -0.1700

Data Index: 7603827 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.2749. Min Act: -0.1700

Data Index: 991563 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.2610. Min Act: -0.1700

Data Index: 2744827 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.2546. Min Act: -0.1700

Data Index: 3240371 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.2364. Min Act: -0.1700

Data Index: 4264580 (Open Web Text)

Max Activating Token Index: 24

Text #13

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.2401. Min Act: -0.1700

Data Index: 4220620 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.2434. Min Act: -0.1700

Data Index: 4675223 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.2273. Min Act: -0.1700

Data Index: 485427 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.2360. Min Act: -0.1700

Data Index: 326814 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.2462. Min Act: -0.1700

Data Index: 1345990 (Open Web Text)

Max Activating Token Index: 13

Text #18

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.2360. Min Act: -0.1700

Data Index: 6133451 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.2360. Min Act: -0.1700

Data Index: 345012 (Open Web Text)

Max Activating Token Index: 3