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

Dataset: Open Web Text

Neuron 1515 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: 2.2248. Min Range: -2.2248

Max Act: 2.2248. Min Act: -0.1700

Data Index: 6012271 (Open Web Text)

Max Activating Token Index: 642

Text #1

Max Range: 2.2248. Min Range: -2.2248

Max Act: 2.1632. Min Act: -0.1700

Data Index: 1635564 (Open Web Text)

Max Activating Token Index: 714

Text #2

Max Range: 2.2248. Min Range: -2.2248

Max Act: 2.1855. Min Act: -0.1700

Data Index: 4651262 (Open Web Text)

Max Activating Token Index: 536

Text #3

Max Range: 2.2248. Min Range: -2.2248

Max Act: 2.1774. Min Act: -0.1700

Data Index: 7093066 (Open Web Text)

Max Activating Token Index: 435

Text #4

Max Range: 2.2248. Min Range: -2.2248

Max Act: 2.1673. Min Act: -0.1700

Data Index: 7825796 (Open Web Text)

Max Activating Token Index: 260

Text #5

Max Range: 2.2248. Min Range: -2.2248

Max Act: 2.1520. Min Act: -0.1700

Data Index: 1428563 (Open Web Text)

Max Activating Token Index: 393

Text #6

Max Range: 2.2248. Min Range: -2.2248

Max Act: 2.1331. Min Act: -0.1700

Data Index: 6996846 (Open Web Text)

Max Activating Token Index: 458

Text #7

Max Range: 2.2248. Min Range: -2.2248

Max Act: 2.1502. Min Act: -0.1700

Data Index: 5609916 (Open Web Text)

Max Activating Token Index: 438

Text #8

Max Range: 2.2248. Min Range: -2.2248

Max Act: 2.1364. Min Act: -0.1700

Data Index: 2025070 (Open Web Text)

Max Activating Token Index: 690

Text #9

Max Range: 2.2248. Min Range: -2.2248

Max Act: 2.1215. Min Act: -0.1700

Data Index: 639498 (Open Web Text)

Max Activating Token Index: 966

Text #10

Max Range: 2.2248. Min Range: -2.2248

Max Act: 2.1225. Min Act: -0.1700

Data Index: 163720 (Open Web Text)

Max Activating Token Index: 331

Text #11

Max Range: 2.2248. Min Range: -2.2248

Max Act: 2.1177. Min Act: -0.1700

Data Index: 3390519 (Open Web Text)

Max Activating Token Index: 517

Text #12

Max Range: 2.2248. Min Range: -2.2248

Max Act: 2.1218. Min Act: -0.1700

Data Index: 2579480 (Open Web Text)

Max Activating Token Index: 76

Text #13

Max Range: 2.2248. Min Range: -2.2248

Max Act: 2.1308. Min Act: -0.1700

Data Index: 3291938 (Open Web Text)

Max Activating Token Index: 668

Text #14

Max Range: 2.2248. Min Range: -2.2248

Max Act: 2.1204. Min Act: -0.1700

Data Index: 6434055 (Open Web Text)

Max Activating Token Index: 112

Text #15

Max Range: 2.2248. Min Range: -2.2248

Max Act: 2.1251. Min Act: -0.1700

Data Index: 4892890 (Open Web Text)

Max Activating Token Index: 616

Text #16

Max Range: 2.2248. Min Range: -2.2248

Max Act: 2.0924. Min Act: -0.1700

Data Index: 5802083 (Open Web Text)

Max Activating Token Index: 904

Text #17

Max Range: 2.2248. Min Range: -2.2248

Max Act: 2.1020. Min Act: -0.1700

Data Index: 266938 (Open Web Text)

Max Activating Token Index: 399

Text #18

Max Range: 2.2248. Min Range: -2.2248

Max Act: 2.0858. Min Act: -0.1700

Data Index: 6552099 (Open Web Text)

Max Activating Token Index: 1022

Text #19

Max Range: 2.2248. Min Range: -2.2248

Max Act: 2.1106. Min Act: -0.1700

Data Index: 2390119 (Open Web Text)

Max Activating Token Index: 216