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

Dataset: Open Web Text

Neuron 1742 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: 4.9647. Min Range: -4.9647

Max Act: 4.9647. Min Act: -0.1700

Data Index: 6622984 (Open Web Text)

Max Activating Token Index: 457

Text #1

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.8524. Min Act: -0.1700

Data Index: 7672975 (Open Web Text)

Max Activating Token Index: 63

Text #2

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.7444. Min Act: -0.1700

Data Index: 6936823 (Open Web Text)

Max Activating Token Index: 821

Text #3

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.6461. Min Act: -0.1700

Data Index: 3637762 (Open Web Text)

Max Activating Token Index: 45

Text #4

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.6104. Min Act: -0.1700

Data Index: 4381012 (Open Web Text)

Max Activating Token Index: 63

Text #5

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.5882. Min Act: -0.1700

Data Index: 4527396 (Open Web Text)

Max Activating Token Index: 529

Text #6

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.5403. Min Act: -0.1700

Data Index: 5103202 (Open Web Text)

Max Activating Token Index: 922

Text #7

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.5512. Min Act: -0.1700

Data Index: 8069851 (Open Web Text)

Max Activating Token Index: 147

Text #8

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.5652. Min Act: -0.1700

Data Index: 1883252 (Open Web Text)

Max Activating Token Index: 741

Text #9

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.5293. Min Act: -0.1700

Data Index: 5485019 (Open Web Text)

Max Activating Token Index: 87

Text #10

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.5372. Min Act: -0.1700

Data Index: 4085230 (Open Web Text)

Max Activating Token Index: 142

Text #11

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.5052. Min Act: -0.1700

Data Index: 7957119 (Open Web Text)

Max Activating Token Index: 945

Text #12

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.5475. Min Act: -0.1700

Data Index: 2718863 (Open Web Text)

Max Activating Token Index: 66

Text #13

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.5491. Min Act: -0.1700

Data Index: 2677119 (Open Web Text)

Max Activating Token Index: 624

Text #14

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.5592. Min Act: -0.1700

Data Index: 2641161 (Open Web Text)

Max Activating Token Index: 541

Text #15

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.5307. Min Act: -0.1700

Data Index: 4683424 (Open Web Text)

Max Activating Token Index: 312

Text #16

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.5299. Min Act: -0.1700

Data Index: 6408668 (Open Web Text)

Max Activating Token Index: 46

Text #17

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.4995. Min Act: -0.1700

Data Index: 3771851 (Open Web Text)

Max Activating Token Index: 1010

Text #18

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.5029. Min Act: -0.1700

Data Index: 3061912 (Open Web Text)

Max Activating Token Index: 40

Text #19

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.4884. Min Act: -0.1700

Data Index: 3828164 (Open Web Text)

Max Activating Token Index: 22