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

Dataset: Open Web Text

Neuron 2714 in Layer 6

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: 3.5365. Min Range: -3.5365

Max Act: 3.5365. Min Act: -0.1700

Data Index: 6348865 (Open Web Text)

Max Activating Token Index: 376

Text #1

Max Range: 3.5365. Min Range: -3.5365

Max Act: 3.2818. Min Act: -0.1700

Data Index: 5960600 (Open Web Text)

Max Activating Token Index: 928

Text #2

Max Range: 3.5365. Min Range: -3.5365

Max Act: 3.2295. Min Act: -0.1700

Data Index: 4228806 (Open Web Text)

Max Activating Token Index: 275

Text #3

Max Range: 3.5365. Min Range: -3.5365

Max Act: 3.2199. Min Act: -0.1700

Data Index: 430160 (Open Web Text)

Max Activating Token Index: 852

Text #4

Max Range: 3.5365. Min Range: -3.5365

Max Act: 3.2084. Min Act: -0.1700

Data Index: 8626591 (Open Web Text)

Max Activating Token Index: 161

Text #5

Max Range: 3.5365. Min Range: -3.5365

Max Act: 3.1778. Min Act: -0.1700

Data Index: 2703187 (Open Web Text)

Max Activating Token Index: 284

Text #6

Max Range: 3.5365. Min Range: -3.5365

Max Act: 3.1275. Min Act: -0.1700

Data Index: 680168 (Open Web Text)

Max Activating Token Index: 457

Text #7

Max Range: 3.5365. Min Range: -3.5365

Max Act: 3.1629. Min Act: -0.1700

Data Index: 221750 (Open Web Text)

Max Activating Token Index: 522

Text #8

Max Range: 3.5365. Min Range: -3.5365

Max Act: 3.1343. Min Act: -0.1700

Data Index: 3642654 (Open Web Text)

Max Activating Token Index: 910

Text #9

Max Range: 3.5365. Min Range: -3.5365

Max Act: 3.1505. Min Act: -0.1700

Data Index: 336978 (Open Web Text)

Max Activating Token Index: 318

Text #10

Max Range: 3.5365. Min Range: -3.5365

Max Act: 3.1345. Min Act: -0.1700

Data Index: 2814772 (Open Web Text)

Max Activating Token Index: 562

Text #11

Max Range: 3.5365. Min Range: -3.5365

Max Act: 3.1319. Min Act: -0.1700

Data Index: 3354165 (Open Web Text)

Max Activating Token Index: 762

Text #12

Max Range: 3.5365. Min Range: -3.5365

Max Act: 3.1650. Min Act: -0.1700

Data Index: 6805478 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 3.5365. Min Range: -3.5365

Max Act: 3.1388. Min Act: -0.1700

Data Index: 6460906 (Open Web Text)

Max Activating Token Index: 400

Text #14

Max Range: 3.5365. Min Range: -3.5365

Max Act: 3.1213. Min Act: -0.1700

Data Index: 6698903 (Open Web Text)

Max Activating Token Index: 732

Text #15

Max Range: 3.5365. Min Range: -3.5365

Max Act: 3.1415. Min Act: -0.1700

Data Index: 2442076 (Open Web Text)

Max Activating Token Index: 242

Text #16

Max Range: 3.5365. Min Range: -3.5365

Max Act: 3.1108. Min Act: -0.1700

Data Index: 3331690 (Open Web Text)

Max Activating Token Index: 367

Text #17

Max Range: 3.5365. Min Range: -3.5365

Max Act: 3.1041. Min Act: -0.1700

Data Index: 3154518 (Open Web Text)

Max Activating Token Index: 271

Text #18

Max Range: 3.5365. Min Range: -3.5365

Max Act: 3.1036. Min Act: -0.1700

Data Index: 2766899 (Open Web Text)

Max Activating Token Index: 625

Text #19

Max Range: 3.5365. Min Range: -3.5365

Max Act: 3.1041. Min Act: -0.1700

Data Index: 4727804 (Open Web Text)

Max Activating Token Index: 1023