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

Dataset: Open Web Text

Neuron 918 in Layer 0

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: 2.8472. Min Range: -2.8472

Max Act: 2.8472. Min Act: -0.1700

Data Index: 5569268 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 2.8472. Min Range: -2.8472

Max Act: 2.8221. Min Act: -0.1700

Data Index: 8331220 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.8472. Min Range: -2.8472

Max Act: 2.8363. Min Act: -0.1700

Data Index: 42627 (Open Web Text)

Max Activating Token Index: 21

Text #3

Max Range: 2.8472. Min Range: -2.8472

Max Act: 2.8187. Min Act: -0.1700

Data Index: 7147430 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.8472. Min Range: -2.8472

Max Act: 2.8077. Min Act: -0.1700

Data Index: 3218190 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 2.8472. Min Range: -2.8472

Max Act: 2.8104. Min Act: -0.1700

Data Index: 4481695 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 2.8472. Min Range: -2.8472

Max Act: 2.7771. Min Act: -0.1700

Data Index: 5274964 (Open Web Text)

Max Activating Token Index: 20

Text #7

Max Range: 2.8472. Min Range: -2.8472

Max Act: 2.7836. Min Act: -0.1700

Data Index: 3701157 (Open Web Text)

Max Activating Token Index: 105

Text #8

Max Range: 2.8472. Min Range: -2.8472

Max Act: 2.7870. Min Act: -0.1700

Data Index: 5243955 (Open Web Text)

Max Activating Token Index: 79

Text #9

Max Range: 2.8472. Min Range: -2.8472

Max Act: 2.7614. Min Act: -0.1700

Data Index: 7513297 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 2.8472. Min Range: -2.8472

Max Act: 2.7657. Min Act: -0.1700

Data Index: 4332079 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 2.8472. Min Range: -2.8472

Max Act: 2.7647. Min Act: -0.1700

Data Index: 4717896 (Open Web Text)

Max Activating Token Index: 36

Text #12

Max Range: 2.8472. Min Range: -2.8472

Max Act: 2.7507. Min Act: -0.1700

Data Index: 8200150 (Open Web Text)

Max Activating Token Index: 588

Text #13

Max Range: 2.8472. Min Range: -2.8472

Max Act: 2.7585. Min Act: -0.1700

Data Index: 5445120 (Open Web Text)

Max Activating Token Index: 13

Text #14

Max Range: 2.8472. Min Range: -2.8472

Max Act: 2.7485. Min Act: -0.1700

Data Index: 6623635 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 2.8472. Min Range: -2.8472

Max Act: 2.7340. Min Act: -0.1700

Data Index: 6755528 (Open Web Text)

Max Activating Token Index: 548

Text #16

Max Range: 2.8472. Min Range: -2.8472

Max Act: 2.7332. Min Act: -0.1700

Data Index: 5046907 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 2.8472. Min Range: -2.8472

Max Act: 2.7422. Min Act: -0.1700

Data Index: 1469441 (Open Web Text)

Max Activating Token Index: 370

Text #18

Max Range: 2.8472. Min Range: -2.8472

Max Act: 2.7306. Min Act: -0.1700

Data Index: 7917015 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 2.8472. Min Range: -2.8472

Max Act: 2.7285. Min Act: -0.1700

Data Index: 6261430 (Open Web Text)

Max Activating Token Index: 238