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

Dataset: Open Web Text

Neuron 2064 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: 5.0458. Min Range: -5.0458

Max Act: 5.0458. Min Act: -0.1700

Data Index: 3215674 (Open Web Text)

Max Activating Token Index: 334

Text #1

Max Range: 5.0458. Min Range: -5.0458

Max Act: 4.7322. Min Act: -0.1700

Data Index: 5758148 (Open Web Text)

Max Activating Token Index: 259

Text #2

Max Range: 5.0458. Min Range: -5.0458

Max Act: 4.6401. Min Act: -0.1700

Data Index: 8182439 (Open Web Text)

Max Activating Token Index: 581

Text #3

Max Range: 5.0458. Min Range: -5.0458

Max Act: 4.4803. Min Act: -0.1700

Data Index: 3211459 (Open Web Text)

Max Activating Token Index: 607

Text #4

Max Range: 5.0458. Min Range: -5.0458

Max Act: 4.4707. Min Act: -0.1700

Data Index: 8687288 (Open Web Text)

Max Activating Token Index: 964

Text #5

Max Range: 5.0458. Min Range: -5.0458

Max Act: 4.4244. Min Act: -0.1700

Data Index: 1639057 (Open Web Text)

Max Activating Token Index: 874

Text #6

Max Range: 5.0458. Min Range: -5.0458

Max Act: 4.4318. Min Act: -0.1700

Data Index: 5190181 (Open Web Text)

Max Activating Token Index: 696

Text #7

Max Range: 5.0458. Min Range: -5.0458

Max Act: 4.4501. Min Act: -0.1700

Data Index: 8512978 (Open Web Text)

Max Activating Token Index: 757

Text #8

Max Range: 5.0458. Min Range: -5.0458

Max Act: 4.4030. Min Act: -0.1700

Data Index: 1814294 (Open Web Text)

Max Activating Token Index: 371

Text #9

Max Range: 5.0458. Min Range: -5.0458

Max Act: 4.3238. Min Act: -0.1700

Data Index: 8557586 (Open Web Text)

Max Activating Token Index: 117

Text #10

Max Range: 5.0458. Min Range: -5.0458

Max Act: 4.3904. Min Act: -0.1700

Data Index: 1850880 (Open Web Text)

Max Activating Token Index: 867

Text #11

Max Range: 5.0458. Min Range: -5.0458

Max Act: 4.3421. Min Act: -0.1700

Data Index: 2832695 (Open Web Text)

Max Activating Token Index: 500

Text #12

Max Range: 5.0458. Min Range: -5.0458

Max Act: 4.3670. Min Act: -0.1700

Data Index: 1212941 (Open Web Text)

Max Activating Token Index: 901

Text #13

Max Range: 5.0458. Min Range: -5.0458

Max Act: 4.3061. Min Act: -0.1700

Data Index: 3864867 (Open Web Text)

Max Activating Token Index: 435

Text #14

Max Range: 5.0458. Min Range: -5.0458

Max Act: 4.3212. Min Act: -0.1700

Data Index: 5334521 (Open Web Text)

Max Activating Token Index: 480

Text #15

Max Range: 5.0458. Min Range: -5.0458

Max Act: 4.2966. Min Act: -0.1700

Data Index: 3911669 (Open Web Text)

Max Activating Token Index: 914

Text #16

Max Range: 5.0458. Min Range: -5.0458

Max Act: 4.3046. Min Act: -0.1700

Data Index: 3746085 (Open Web Text)

Max Activating Token Index: 264

Text #17

Max Range: 5.0458. Min Range: -5.0458

Max Act: 4.2383. Min Act: -0.1700

Data Index: 7533918 (Open Web Text)

Max Activating Token Index: 519

Text #18

Max Range: 5.0458. Min Range: -5.0458

Max Act: 4.2589. Min Act: -0.1700

Data Index: 4215286 (Open Web Text)

Max Activating Token Index: 453

Text #19

Max Range: 5.0458. Min Range: -5.0458

Max Act: 4.2636. Min Act: -0.1700

Data Index: 7232215 (Open Web Text)

Max Activating Token Index: 839