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

Dataset: Open Web Text

Neuron 2377 in Layer 5

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: 3.2520. Min Range: -3.2520

Max Act: 3.2520. Min Act: -0.1700

Data Index: 2657882 (Open Web Text)

Max Activating Token Index: 952

Text #1

Max Range: 3.2520. Min Range: -3.2520

Max Act: 3.1955. Min Act: -0.1700

Data Index: 3827085 (Open Web Text)

Max Activating Token Index: 396

Text #2

Max Range: 3.2520. Min Range: -3.2520

Max Act: 3.1740. Min Act: -0.1700

Data Index: 3213028 (Open Web Text)

Max Activating Token Index: 496

Text #3

Max Range: 3.2520. Min Range: -3.2520

Max Act: 3.1503. Min Act: -0.1700

Data Index: 849994 (Open Web Text)

Max Activating Token Index: 589

Text #4

Max Range: 3.2520. Min Range: -3.2520

Max Act: 3.1444. Min Act: -0.1700

Data Index: 7636041 (Open Web Text)

Max Activating Token Index: 120

Text #5

Max Range: 3.2520. Min Range: -3.2520

Max Act: 3.1529. Min Act: -0.1700

Data Index: 1387124 (Open Web Text)

Max Activating Token Index: 380

Text #6

Max Range: 3.2520. Min Range: -3.2520

Max Act: 3.1108. Min Act: -0.1700

Data Index: 3028692 (Open Web Text)

Max Activating Token Index: 342

Text #7

Max Range: 3.2520. Min Range: -3.2520

Max Act: 3.0842. Min Act: -0.1700

Data Index: 4857923 (Open Web Text)

Max Activating Token Index: 936

Text #8

Max Range: 3.2520. Min Range: -3.2520

Max Act: 3.0343. Min Act: -0.1700

Data Index: 3538120 (Open Web Text)

Max Activating Token Index: 979

Text #9

Max Range: 3.2520. Min Range: -3.2520

Max Act: 3.0505. Min Act: -0.1700

Data Index: 1801828 (Open Web Text)

Max Activating Token Index: 335

Text #10

Max Range: 3.2520. Min Range: -3.2520

Max Act: 3.0351. Min Act: -0.1700

Data Index: 1526849 (Open Web Text)

Max Activating Token Index: 846

Text #11

Max Range: 3.2520. Min Range: -3.2520

Max Act: 3.0241. Min Act: -0.1700

Data Index: 4497110 (Open Web Text)

Max Activating Token Index: 981

Text #12

Max Range: 3.2520. Min Range: -3.2520

Max Act: 2.9760. Min Act: -0.1700

Data Index: 4863899 (Open Web Text)

Max Activating Token Index: 442

Text #13

Max Range: 3.2520. Min Range: -3.2520

Max Act: 2.9788. Min Act: -0.1700

Data Index: 2957970 (Open Web Text)

Max Activating Token Index: 837

Text #14

Max Range: 3.2520. Min Range: -3.2520

Max Act: 2.9859. Min Act: -0.1700

Data Index: 4935801 (Open Web Text)

Max Activating Token Index: 796

Text #15

Max Range: 3.2520. Min Range: -3.2520

Max Act: 2.9548. Min Act: -0.1700

Data Index: 1033270 (Open Web Text)

Max Activating Token Index: 435

Text #16

Max Range: 3.2520. Min Range: -3.2520

Max Act: 2.9606. Min Act: -0.1700

Data Index: 7477349 (Open Web Text)

Max Activating Token Index: 393

Text #17

Max Range: 3.2520. Min Range: -3.2520

Max Act: 2.9606. Min Act: -0.1700

Data Index: 8750906 (Open Web Text)

Max Activating Token Index: 799

Text #18

Max Range: 3.2520. Min Range: -3.2520

Max Act: 2.9484. Min Act: -0.1700

Data Index: 7525903 (Open Web Text)

Max Activating Token Index: 395

Text #19

Max Range: 3.2520. Min Range: -3.2520

Max Act: 2.9408. Min Act: -0.1700

Data Index: 855273 (Open Web Text)

Max Activating Token Index: 754