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

Dataset: Open Web Text

Neuron 1282 in Layer 1

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: 5.7866. Min Range: -5.7866

Max Act: 5.7866. Min Act: -0.1700

Data Index: 3364113 (Open Web Text)

Max Activating Token Index: 201

Text #1

Max Range: 5.7866. Min Range: -5.7866

Max Act: 5.6976. Min Act: -0.1700

Data Index: 741743 (Open Web Text)

Max Activating Token Index: 556

Text #2

Max Range: 5.7866. Min Range: -5.7866

Max Act: 5.6848. Min Act: -0.1700

Data Index: 4583347 (Open Web Text)

Max Activating Token Index: 23

Text #3

Max Range: 5.7866. Min Range: -5.7866

Max Act: 5.6712. Min Act: -0.1700

Data Index: 600729 (Open Web Text)

Max Activating Token Index: 976

Text #4

Max Range: 5.7866. Min Range: -5.7866

Max Act: 5.6225. Min Act: -0.1700

Data Index: 7004503 (Open Web Text)

Max Activating Token Index: 268

Text #5

Max Range: 5.7866. Min Range: -5.7866

Max Act: 5.6182. Min Act: -0.1700

Data Index: 4583359 (Open Web Text)

Max Activating Token Index: 345

Text #6

Max Range: 5.7866. Min Range: -5.7866

Max Act: 5.6147. Min Act: -0.1700

Data Index: 4739266 (Open Web Text)

Max Activating Token Index: 38

Text #7

Max Range: 5.7866. Min Range: -5.7866

Max Act: 5.6275. Min Act: -0.1700

Data Index: 7004511 (Open Web Text)

Max Activating Token Index: 282

Text #8

Max Range: 5.7866. Min Range: -5.7866

Max Act: 5.5882. Min Act: -0.1695

Data Index: 3686071 (Open Web Text)

Max Activating Token Index: 23

Text #9

Max Range: 5.7866. Min Range: -5.7866

Max Act: 5.6096. Min Act: -0.1700

Data Index: 1527778 (Open Web Text)

Max Activating Token Index: 53

Text #10

Max Range: 5.7866. Min Range: -5.7866

Max Act: 5.5815. Min Act: -0.1700

Data Index: 2116695 (Open Web Text)

Max Activating Token Index: 21

Text #11

Max Range: 5.7866. Min Range: -5.7866

Max Act: 5.5681. Min Act: -0.1700

Data Index: 2327296 (Open Web Text)

Max Activating Token Index: 323

Text #12

Max Range: 5.7866. Min Range: -5.7866

Max Act: 5.5734. Min Act: -0.1700

Data Index: 3499637 (Open Web Text)

Max Activating Token Index: 83

Text #13

Max Range: 5.7866. Min Range: -5.7866

Max Act: 5.5790. Min Act: -0.1700

Data Index: 5321208 (Open Web Text)

Max Activating Token Index: 24

Text #14

Max Range: 5.7866. Min Range: -5.7866

Max Act: 5.5799. Min Act: -0.1700

Data Index: 7498139 (Open Web Text)

Max Activating Token Index: 462

Text #15

Max Range: 5.7866. Min Range: -5.7866

Max Act: 5.5569. Min Act: -0.1700

Data Index: 8155914 (Open Web Text)

Max Activating Token Index: 398

Text #16

Max Range: 5.7866. Min Range: -5.7866

Max Act: 5.5602. Min Act: -0.1700

Data Index: 4221725 (Open Web Text)

Max Activating Token Index: 51

Text #17

Max Range: 5.7866. Min Range: -5.7866

Max Act: 5.5815. Min Act: -0.1700

Data Index: 5843364 (Open Web Text)

Max Activating Token Index: 802

Text #18

Max Range: 5.7866. Min Range: -5.7866

Max Act: 5.5829. Min Act: -0.1700

Data Index: 7801194 (Open Web Text)

Max Activating Token Index: 38

Text #19

Max Range: 5.7866. Min Range: -5.7866

Max Act: 5.5398. Min Act: -0.1700

Data Index: 7032393 (Open Web Text)

Max Activating Token Index: 58