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

Dataset: Open Web Text

Neuron 1522 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: 1.8542. Min Range: -1.8542

Max Act: 1.8542. Min Act: -0.1700

Data Index: 3121178 (Open Web Text)

Max Activating Token Index: 344

Text #1

Max Range: 1.8542. Min Range: -1.8542

Max Act: 1.8241. Min Act: -0.1700

Data Index: 7366142 (Open Web Text)

Max Activating Token Index: 306

Text #2

Max Range: 1.8542. Min Range: -1.8542

Max Act: 1.8029. Min Act: -0.1700

Data Index: 7471685 (Open Web Text)

Max Activating Token Index: 478

Text #3

Max Range: 1.8542. Min Range: -1.8542

Max Act: 1.7937. Min Act: -0.1700

Data Index: 5965585 (Open Web Text)

Max Activating Token Index: 409

Text #4

Max Range: 1.8542. Min Range: -1.8542

Max Act: 1.7677. Min Act: -0.1700

Data Index: 4991996 (Open Web Text)

Max Activating Token Index: 232

Text #5

Max Range: 1.8542. Min Range: -1.8542

Max Act: 1.7714. Min Act: -0.1700

Data Index: 5965561 (Open Web Text)

Max Activating Token Index: 640

Text #6

Max Range: 1.8542. Min Range: -1.8542

Max Act: 1.7497. Min Act: -0.1700

Data Index: 5970749 (Open Web Text)

Max Activating Token Index: 318

Text #7

Max Range: 1.8542. Min Range: -1.8542

Max Act: 1.7488. Min Act: -0.1700

Data Index: 4991992 (Open Web Text)

Max Activating Token Index: 199

Text #8

Max Range: 1.8542. Min Range: -1.8542

Max Act: 1.7432. Min Act: -0.1700

Data Index: 3297015 (Open Web Text)

Max Activating Token Index: 787

Text #9

Max Range: 1.8542. Min Range: -1.8542

Max Act: 1.7443. Min Act: -0.1700

Data Index: 6440056 (Open Web Text)

Max Activating Token Index: 391

Text #10

Max Range: 1.8542. Min Range: -1.8542

Max Act: 1.7443. Min Act: -0.1699

Data Index: 5544311 (Open Web Text)

Max Activating Token Index: 732

Text #11

Max Range: 1.8542. Min Range: -1.8542

Max Act: 1.7398. Min Act: -0.1700

Data Index: 4397430 (Open Web Text)

Max Activating Token Index: 315

Text #12

Max Range: 1.8542. Min Range: -1.8542

Max Act: 1.7267. Min Act: -0.1700

Data Index: 1167837 (Open Web Text)

Max Activating Token Index: 651

Text #13

Max Range: 1.8542. Min Range: -1.8542

Max Act: 1.7365. Min Act: -0.1700

Data Index: 5970757 (Open Web Text)

Max Activating Token Index: 333

Text #14

Max Range: 1.8542. Min Range: -1.8542

Max Act: 1.7119. Min Act: -0.1700

Data Index: 5965565 (Open Web Text)

Max Activating Token Index: 928

Text #15

Max Range: 1.8542. Min Range: -1.8542

Max Act: 1.7095. Min Act: -0.1700

Data Index: 112104 (Open Web Text)

Max Activating Token Index: 418

Text #16

Max Range: 1.8542. Min Range: -1.8542

Max Act: 1.7105. Min Act: -0.1700

Data Index: 5861224 (Open Web Text)

Max Activating Token Index: 417

Text #17

Max Range: 1.8542. Min Range: -1.8542

Max Act: 1.6957. Min Act: -0.1700

Data Index: 8172120 (Open Web Text)

Max Activating Token Index: 741

Text #18

Max Range: 1.8542. Min Range: -1.8542

Max Act: 1.6954. Min Act: -0.1700

Data Index: 6415893 (Open Web Text)

Max Activating Token Index: 543

Text #19

Max Range: 1.8542. Min Range: -1.8542

Max Act: 1.6876. Min Act: -0.1700

Data Index: 7398223 (Open Web Text)

Max Activating Token Index: 204