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

Dataset: Open Web Text

Neuron 672 in Layer 4

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: 4.7516. Min Range: -4.7516

Max Act: 4.7516. Min Act: -0.1700

Data Index: 165091 (Open Web Text)

Max Activating Token Index: 453

Text #1

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.6445. Min Act: -0.1700

Data Index: 5509031 (Open Web Text)

Max Activating Token Index: 439

Text #2

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.6573. Min Act: -0.1700

Data Index: 6219116 (Open Web Text)

Max Activating Token Index: 676

Text #3

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.6537. Min Act: -0.1700

Data Index: 6973955 (Open Web Text)

Max Activating Token Index: 487

Text #4

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.6394. Min Act: -0.1700

Data Index: 2129201 (Open Web Text)

Max Activating Token Index: 688

Text #5

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.6285. Min Act: -0.1700

Data Index: 446705 (Open Web Text)

Max Activating Token Index: 801

Text #6

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.6422. Min Act: -0.1700

Data Index: 2815349 (Open Web Text)

Max Activating Token Index: 585

Text #7

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.6029. Min Act: -0.1700

Data Index: 3421642 (Open Web Text)

Max Activating Token Index: 56

Text #8

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.6226. Min Act: -0.1700

Data Index: 8619858 (Open Web Text)

Max Activating Token Index: 45

Text #9

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.5668. Min Act: -0.1700

Data Index: 3513705 (Open Web Text)

Max Activating Token Index: 92

Text #10

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.5293. Min Act: -0.1700

Data Index: 3959868 (Open Web Text)

Max Activating Token Index: 728

Text #11

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.5835. Min Act: -0.1700

Data Index: 3381517 (Open Web Text)

Max Activating Token Index: 521

Text #12

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.5807. Min Act: -0.1700

Data Index: 7185316 (Open Web Text)

Max Activating Token Index: 100

Text #13

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.6188. Min Act: -0.1700

Data Index: 4985552 (Open Web Text)

Max Activating Token Index: 695

Text #14

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.5456. Min Act: -0.1700

Data Index: 2341937 (Open Web Text)

Max Activating Token Index: 868

Text #15

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.5458. Min Act: -0.1700

Data Index: 1267642 (Open Web Text)

Max Activating Token Index: 526

Text #16

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.5484. Min Act: -0.1700

Data Index: 2039579 (Open Web Text)

Max Activating Token Index: 234

Text #17

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.5227. Min Act: -0.1700

Data Index: 6246687 (Open Web Text)

Max Activating Token Index: 24

Text #18

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.5170. Min Act: -0.1700

Data Index: 1473100 (Open Web Text)

Max Activating Token Index: 846

Text #19

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.5266. Min Act: -0.1700

Data Index: 2146681 (Open Web Text)

Max Activating Token Index: 553