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

Dataset: Open Web Text

Neuron 968 in Layer 5

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: 4.6026. Min Range: -4.6026

Max Act: 4.6026. Min Act: -0.1700

Data Index: 4545055 (Open Web Text)

Max Activating Token Index: 678

Text #1

Max Range: 4.6026. Min Range: -4.6026

Max Act: 4.5848. Min Act: -0.1700

Data Index: 791293 (Open Web Text)

Max Activating Token Index: 47

Text #2

Max Range: 4.6026. Min Range: -4.6026

Max Act: 4.5376. Min Act: -0.1700

Data Index: 2366980 (Open Web Text)

Max Activating Token Index: 728

Text #3

Max Range: 4.6026. Min Range: -4.6026

Max Act: 4.5387. Min Act: -0.1700

Data Index: 6107874 (Open Web Text)

Max Activating Token Index: 542

Text #4

Max Range: 4.6026. Min Range: -4.6026

Max Act: 4.4806. Min Act: -0.1700

Data Index: 2106039 (Open Web Text)

Max Activating Token Index: 729

Text #5

Max Range: 4.6026. Min Range: -4.6026

Max Act: 4.4692. Min Act: -0.1700

Data Index: 8816556 (Open Web Text)

Max Activating Token Index: 110

Text #6

Max Range: 4.6026. Min Range: -4.6026

Max Act: 4.4916. Min Act: -0.1700

Data Index: 6714690 (Open Web Text)

Max Activating Token Index: 420

Text #7

Max Range: 4.6026. Min Range: -4.6026

Max Act: 4.4646. Min Act: -0.1700

Data Index: 5166848 (Open Web Text)

Max Activating Token Index: 671

Text #8

Max Range: 4.6026. Min Range: -4.6026

Max Act: 4.4738. Min Act: -0.1700

Data Index: 7271734 (Open Web Text)

Max Activating Token Index: 878

Text #9

Max Range: 4.6026. Min Range: -4.6026

Max Act: 4.3936. Min Act: -0.1700

Data Index: 1893377 (Open Web Text)

Max Activating Token Index: 75

Text #10

Max Range: 4.6026. Min Range: -4.6026

Max Act: 4.4193. Min Act: -0.1700

Data Index: 7257391 (Open Web Text)

Max Activating Token Index: 119

Text #11

Max Range: 4.6026. Min Range: -4.6026

Max Act: 4.3841. Min Act: -0.1700

Data Index: 1483552 (Open Web Text)

Max Activating Token Index: 719

Text #12

Max Range: 4.6026. Min Range: -4.6026

Max Act: 4.3656. Min Act: -0.1700

Data Index: 3736310 (Open Web Text)

Max Activating Token Index: 74

Text #13

Max Range: 4.6026. Min Range: -4.6026

Max Act: 4.3810. Min Act: -0.1700

Data Index: 5118355 (Open Web Text)

Max Activating Token Index: 803

Text #14

Max Range: 4.6026. Min Range: -4.6026

Max Act: 4.3941. Min Act: -0.1700

Data Index: 7635786 (Open Web Text)

Max Activating Token Index: 900

Text #15

Max Range: 4.6026. Min Range: -4.6026

Max Act: 4.3381. Min Act: -0.1700

Data Index: 3966322 (Open Web Text)

Max Activating Token Index: 701

Text #16

Max Range: 4.6026. Min Range: -4.6026

Max Act: 4.3275. Min Act: -0.1700

Data Index: 2409729 (Open Web Text)

Max Activating Token Index: 138

Text #17

Max Range: 4.6026. Min Range: -4.6026

Max Act: 4.3387. Min Act: -0.1700

Data Index: 3395023 (Open Web Text)

Max Activating Token Index: 575

Text #18

Max Range: 4.6026. Min Range: -4.6026

Max Act: 4.3540. Min Act: -0.1700

Data Index: 580644 (Open Web Text)

Max Activating Token Index: 229

Text #19

Max Range: 4.6026. Min Range: -4.6026

Max Act: 4.3547. Min Act: -0.1700

Data Index: 841427 (Open Web Text)

Max Activating Token Index: 420