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

Dataset: Open Web Text

Neuron 2183 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: 1.4932. Min Range: -1.4932

Max Act: 1.4932. Min Act: -0.1413

Data Index: 2705884 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.4657. Min Act: -0.1200

Data Index: 819327 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.4702. Min Act: -0.1338

Data Index: 4387331 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.4537. Min Act: -0.1628

Data Index: 6646799 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.4536. Min Act: -0.1472

Data Index: 7389087 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.4640. Min Act: -0.1472

Data Index: 8244348 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.4410. Min Act: -0.1260

Data Index: 8660219 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.4339. Min Act: -0.1319

Data Index: 1599019 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.4416. Min Act: -0.1162

Data Index: 117540 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.4414. Min Act: -0.1484

Data Index: 1158309 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.4477. Min Act: -0.1357

Data Index: 8550812 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.4449. Min Act: -0.1530

Data Index: 5964798 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.4405. Min Act: -0.1254

Data Index: 5618839 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.4275. Min Act: -0.1227

Data Index: 1955459 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.4243. Min Act: -0.1521

Data Index: 1766044 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.4334. Min Act: -0.1508

Data Index: 601318 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.4376. Min Act: -0.1359

Data Index: 3233546 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.4220. Min Act: -0.1336

Data Index: 8380712 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.4270. Min Act: -0.1514

Data Index: 621451 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.4216. Min Act: -0.1220

Data Index: 6269120 (Open Web Text)

Max Activating Token Index: 1023