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

Dataset: Open Web Text

Neuron 333 in Layer 2

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: 1.2680. Min Range: -1.2680

Max Act: 1.2680. Min Act: -0.1698

Data Index: 398635 (Open Web Text)

Max Activating Token Index: 903

Text #1

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.2594. Min Act: -0.1700

Data Index: 1990069 (Open Web Text)

Max Activating Token Index: 802

Text #2

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.2537. Min Act: -0.1698

Data Index: 6626845 (Open Web Text)

Max Activating Token Index: 277

Text #3

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.2324. Min Act: -0.1700

Data Index: 4813416 (Open Web Text)

Max Activating Token Index: 266

Text #4

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.2273. Min Act: -0.1700

Data Index: 4953495 (Open Web Text)

Max Activating Token Index: 426

Text #5

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.2341. Min Act: -0.1700

Data Index: 7974740 (Open Web Text)

Max Activating Token Index: 795

Text #6

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.2230. Min Act: -0.1700

Data Index: 3366259 (Open Web Text)

Max Activating Token Index: 250

Text #7

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.2244. Min Act: -0.1700

Data Index: 1363328 (Open Web Text)

Max Activating Token Index: 103

Text #8

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.2294. Min Act: -0.1700

Data Index: 3641581 (Open Web Text)

Max Activating Token Index: 392

Text #9

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.2287. Min Act: -0.1700

Data Index: 7503969 (Open Web Text)

Max Activating Token Index: 183

Text #10

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.2175. Min Act: -0.1700

Data Index: 3641580 (Open Web Text)

Max Activating Token Index: 773

Text #11

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.2109. Min Act: -0.1658

Data Index: 4996593 (Open Web Text)

Max Activating Token Index: 288

Text #12

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.2160. Min Act: -0.1700

Data Index: 6672565 (Open Web Text)

Max Activating Token Index: 748

Text #13

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.2122. Min Act: -0.1700

Data Index: 6198328 (Open Web Text)

Max Activating Token Index: 38

Text #14

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.2113. Min Act: -0.1700

Data Index: 4069413 (Open Web Text)

Max Activating Token Index: 700

Text #15

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.1993. Min Act: -0.1700

Data Index: 3604161 (Open Web Text)

Max Activating Token Index: 596

Text #16

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.2038. Min Act: -0.1699

Data Index: 5996308 (Open Web Text)

Max Activating Token Index: 370

Text #17

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.2076. Min Act: -0.1700

Data Index: 4823075 (Open Web Text)

Max Activating Token Index: 909

Text #18

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.2061. Min Act: -0.1700

Data Index: 5496869 (Open Web Text)

Max Activating Token Index: 471

Text #19

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.1950. Min Act: -0.1478

Data Index: 4905788 (Open Web Text)

Max Activating Token Index: 19