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

Dataset: Open Web Text

Neuron 1083 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: 4.4759. Min Range: -4.4759

Max Act: 4.4333. Min Act: -0.1700

Data Index: 5025041 (Open Web Text)

Max Activating Token Index: 359

Text #1

Max Range: 4.4759. Min Range: -4.4759

Max Act: 4.4303. Min Act: -0.1700

Data Index: 3757983 (Open Web Text)

Max Activating Token Index: 865

Text #2

Max Range: 4.4759. Min Range: -4.4759

Max Act: 4.4759. Min Act: -0.1700

Data Index: 4521936 (Open Web Text)

Max Activating Token Index: 378

Text #3

Max Range: 4.4759. Min Range: -4.4759

Max Act: 4.4254. Min Act: -0.1700

Data Index: 1360841 (Open Web Text)

Max Activating Token Index: 880

Text #4

Max Range: 4.4759. Min Range: -4.4759

Max Act: 4.4096. Min Act: -0.1700

Data Index: 8019324 (Open Web Text)

Max Activating Token Index: 716

Text #5

Max Range: 4.4759. Min Range: -4.4759

Max Act: 4.4379. Min Act: -0.1700

Data Index: 7547562 (Open Web Text)

Max Activating Token Index: 879

Text #6

Max Range: 4.4759. Min Range: -4.4759

Max Act: 4.4060. Min Act: -0.1700

Data Index: 5597650 (Open Web Text)

Max Activating Token Index: 39

Text #7

Max Range: 4.4759. Min Range: -4.4759

Max Act: 4.4301. Min Act: -0.1700

Data Index: 8448549 (Open Web Text)

Max Activating Token Index: 625

Text #8

Max Range: 4.4759. Min Range: -4.4759

Max Act: 4.3918. Min Act: -0.1700

Data Index: 3161356 (Open Web Text)

Max Activating Token Index: 638

Text #9

Max Range: 4.4759. Min Range: -4.4759

Max Act: 4.3413. Min Act: -0.1700

Data Index: 1151922 (Open Web Text)

Max Activating Token Index: 535

Text #10

Max Range: 4.4759. Min Range: -4.4759

Max Act: 4.3975. Min Act: -0.1700

Data Index: 2987987 (Open Web Text)

Max Activating Token Index: 182

Text #11

Max Range: 4.4759. Min Range: -4.4759

Max Act: 4.3933. Min Act: -0.1700

Data Index: 3623500 (Open Web Text)

Max Activating Token Index: 435

Text #12

Max Range: 4.4759. Min Range: -4.4759

Max Act: 4.3890. Min Act: -0.1700

Data Index: 8569628 (Open Web Text)

Max Activating Token Index: 315

Text #13

Max Range: 4.4759. Min Range: -4.4759

Max Act: 4.3385. Min Act: -0.1700

Data Index: 5441561 (Open Web Text)

Max Activating Token Index: 800

Text #14

Max Range: 4.4759. Min Range: -4.4759

Max Act: 4.3058. Min Act: -0.1700

Data Index: 7761141 (Open Web Text)

Max Activating Token Index: 686

Text #15

Max Range: 4.4759. Min Range: -4.4759

Max Act: 4.3399. Min Act: -0.1700

Data Index: 5626762 (Open Web Text)

Max Activating Token Index: 1019

Text #16

Max Range: 4.4759. Min Range: -4.4759

Max Act: 4.3222. Min Act: -0.1699

Data Index: 7347482 (Open Web Text)

Max Activating Token Index: 555

Text #17

Max Range: 4.4759. Min Range: -4.4759

Max Act: 4.3618. Min Act: -0.1700

Data Index: 2550456 (Open Web Text)

Max Activating Token Index: 969

Text #18

Max Range: 4.4759. Min Range: -4.4759

Max Act: 4.3236. Min Act: -0.1700

Data Index: 7414324 (Open Web Text)

Max Activating Token Index: 615

Text #19

Max Range: 4.4759. Min Range: -4.4759

Max Act: 4.3250. Min Act: -0.1700

Data Index: 4885643 (Open Web Text)

Max Activating Token Index: 520