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

Dataset: Open Web Text

Neuron 3027 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: 3.3878. Min Range: -3.3878

Max Act: 3.3655. Min Act: -0.1700

Data Index: 2446963 (Open Web Text)

Max Activating Token Index: 45

Text #1

Max Range: 3.3878. Min Range: -3.3878

Max Act: 3.3676. Min Act: -0.1700

Data Index: 2841504 (Open Web Text)

Max Activating Token Index: 956

Text #2

Max Range: 3.3878. Min Range: -3.3878

Max Act: 3.3878. Min Act: -0.1700

Data Index: 1481957 (Open Web Text)

Max Activating Token Index: 19

Text #3

Max Range: 3.3878. Min Range: -3.3878

Max Act: 3.3841. Min Act: -0.1700

Data Index: 3027017 (Open Web Text)

Max Activating Token Index: 661

Text #4

Max Range: 3.3878. Min Range: -3.3878

Max Act: 3.3681. Min Act: -0.1700

Data Index: 4159353 (Open Web Text)

Max Activating Token Index: 35

Text #5

Max Range: 3.3878. Min Range: -3.3878

Max Act: 3.3751. Min Act: -0.1700

Data Index: 6744882 (Open Web Text)

Max Activating Token Index: 82

Text #6

Max Range: 3.3878. Min Range: -3.3878

Max Act: 3.3501. Min Act: -0.1700

Data Index: 7404934 (Open Web Text)

Max Activating Token Index: 287

Text #7

Max Range: 3.3878. Min Range: -3.3878

Max Act: 3.3553. Min Act: -0.1700

Data Index: 1957058 (Open Web Text)

Max Activating Token Index: 715

Text #8

Max Range: 3.3878. Min Range: -3.3878

Max Act: 3.3472. Min Act: -0.1700

Data Index: 2841502 (Open Web Text)

Max Activating Token Index: 890

Text #9

Max Range: 3.3878. Min Range: -3.3878

Max Act: 3.3333. Min Act: -0.1700

Data Index: 1127198 (Open Web Text)

Max Activating Token Index: 19

Text #10

Max Range: 3.3878. Min Range: -3.3878

Max Act: 3.3656. Min Act: -0.1700

Data Index: 2471740 (Open Web Text)

Max Activating Token Index: 847

Text #11

Max Range: 3.3878. Min Range: -3.3878

Max Act: 3.3302. Min Act: -0.1700

Data Index: 332080 (Open Web Text)

Max Activating Token Index: 623

Text #12

Max Range: 3.3878. Min Range: -3.3878

Max Act: 3.3572. Min Act: -0.1700

Data Index: 7348584 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 3.3878. Min Range: -3.3878

Max Act: 3.3382. Min Act: -0.1700

Data Index: 6538110 (Open Web Text)

Max Activating Token Index: 502

Text #14

Max Range: 3.3878. Min Range: -3.3878

Max Act: 3.3493. Min Act: -0.1700

Data Index: 5444371 (Open Web Text)

Max Activating Token Index: 537

Text #15

Max Range: 3.3878. Min Range: -3.3878

Max Act: 3.3572. Min Act: -0.1700

Data Index: 5036183 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 3.3878. Min Range: -3.3878

Max Act: 3.3408. Min Act: -0.1700

Data Index: 4041172 (Open Web Text)

Max Activating Token Index: 687

Text #17

Max Range: 3.3878. Min Range: -3.3878

Max Act: 3.3348. Min Act: -0.1700

Data Index: 3712713 (Open Web Text)

Max Activating Token Index: 637

Text #18

Max Range: 3.3878. Min Range: -3.3878

Max Act: 3.3572. Min Act: -0.1700

Data Index: 2446961 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.3878. Min Range: -3.3878

Max Act: 3.3572. Min Act: -0.1700

Data Index: 2866644 (Open Web Text)

Max Activating Token Index: 8