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

Dataset: Open Web Text

Neuron 73 in Layer 3

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: 5.6894. Min Range: -5.6894

Max Act: 5.6894. Min Act: -0.1700

Data Index: 2223625 (Open Web Text)

Max Activating Token Index: 861

Text #1

Max Range: 5.6894. Min Range: -5.6894

Max Act: 5.5262. Min Act: -0.1700

Data Index: 3540090 (Open Web Text)

Max Activating Token Index: 272

Text #2

Max Range: 5.6894. Min Range: -5.6894

Max Act: 5.5145. Min Act: -0.1700

Data Index: 1721666 (Open Web Text)

Max Activating Token Index: 700

Text #3

Max Range: 5.6894. Min Range: -5.6894

Max Act: 5.4299. Min Act: -0.1700

Data Index: 5595576 (Open Web Text)

Max Activating Token Index: 905

Text #4

Max Range: 5.6894. Min Range: -5.6894

Max Act: 5.4241. Min Act: -0.1700

Data Index: 4913846 (Open Web Text)

Max Activating Token Index: 999

Text #5

Max Range: 5.6894. Min Range: -5.6894

Max Act: 5.4178. Min Act: -0.1700

Data Index: 8076510 (Open Web Text)

Max Activating Token Index: 255

Text #6

Max Range: 5.6894. Min Range: -5.6894

Max Act: 5.4274. Min Act: -0.1700

Data Index: 3973542 (Open Web Text)

Max Activating Token Index: 458

Text #7

Max Range: 5.6894. Min Range: -5.6894

Max Act: 5.4228. Min Act: -0.1700

Data Index: 2595069 (Open Web Text)

Max Activating Token Index: 693

Text #8

Max Range: 5.6894. Min Range: -5.6894

Max Act: 5.4041. Min Act: -0.1700

Data Index: 425254 (Open Web Text)

Max Activating Token Index: 252

Text #9

Max Range: 5.6894. Min Range: -5.6894

Max Act: 5.3703. Min Act: -0.1700

Data Index: 5882520 (Open Web Text)

Max Activating Token Index: 391

Text #10

Max Range: 5.6894. Min Range: -5.6894

Max Act: 5.3553. Min Act: -0.1700

Data Index: 1388079 (Open Web Text)

Max Activating Token Index: 205

Text #11

Max Range: 5.6894. Min Range: -5.6894

Max Act: 5.3654. Min Act: -0.1700

Data Index: 7668852 (Open Web Text)

Max Activating Token Index: 881

Text #12

Max Range: 5.6894. Min Range: -5.6894

Max Act: 5.3765. Min Act: -0.1700

Data Index: 3977415 (Open Web Text)

Max Activating Token Index: 679

Text #13

Max Range: 5.6894. Min Range: -5.6894

Max Act: 5.3176. Min Act: -0.1700

Data Index: 1890185 (Open Web Text)

Max Activating Token Index: 981

Text #14

Max Range: 5.6894. Min Range: -5.6894

Max Act: 5.3367. Min Act: -0.1700

Data Index: 6690760 (Open Web Text)

Max Activating Token Index: 299

Text #15

Max Range: 5.6894. Min Range: -5.6894

Max Act: 5.3380. Min Act: -0.1700

Data Index: 8306441 (Open Web Text)

Max Activating Token Index: 405

Text #16

Max Range: 5.6894. Min Range: -5.6894

Max Act: 5.3307. Min Act: -0.1700

Data Index: 3748539 (Open Web Text)

Max Activating Token Index: 534

Text #17

Max Range: 5.6894. Min Range: -5.6894

Max Act: 5.3598. Min Act: -0.1700

Data Index: 4873643 (Open Web Text)

Max Activating Token Index: 973

Text #18

Max Range: 5.6894. Min Range: -5.6894

Max Act: 5.3067. Min Act: -0.1700

Data Index: 4489202 (Open Web Text)

Max Activating Token Index: 302

Text #19

Max Range: 5.6894. Min Range: -5.6894

Max Act: 5.3002. Min Act: -0.1700

Data Index: 4750047 (Open Web Text)

Max Activating Token Index: 499