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

Dataset: Open Web Text

Neuron 2564 in Layer 2

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: 4.5760. Min Range: -4.5760

Max Act: 4.5760. Min Act: -0.1700

Data Index: 2777808 (Open Web Text)

Max Activating Token Index: 43

Text #1

Max Range: 4.5760. Min Range: -4.5760

Max Act: 4.2723. Min Act: -0.1700

Data Index: 1274333 (Open Web Text)

Max Activating Token Index: 781

Text #2

Max Range: 4.5760. Min Range: -4.5760

Max Act: 4.2465. Min Act: -0.1700

Data Index: 8582508 (Open Web Text)

Max Activating Token Index: 55

Text #3

Max Range: 4.5760. Min Range: -4.5760

Max Act: 4.1730. Min Act: -0.1700

Data Index: 5104596 (Open Web Text)

Max Activating Token Index: 257

Text #4

Max Range: 4.5760. Min Range: -4.5760

Max Act: 4.1579. Min Act: -0.1700

Data Index: 6814401 (Open Web Text)

Max Activating Token Index: 83

Text #5

Max Range: 4.5760. Min Range: -4.5760

Max Act: 4.1638. Min Act: -0.1700

Data Index: 3388006 (Open Web Text)

Max Activating Token Index: 95

Text #6

Max Range: 4.5760. Min Range: -4.5760

Max Act: 4.1605. Min Act: -0.1700

Data Index: 2907236 (Open Web Text)

Max Activating Token Index: 56

Text #7

Max Range: 4.5760. Min Range: -4.5760

Max Act: 4.1399. Min Act: -0.1700

Data Index: 8249553 (Open Web Text)

Max Activating Token Index: 271

Text #8

Max Range: 4.5760. Min Range: -4.5760

Max Act: 4.1302. Min Act: -0.1700

Data Index: 7983739 (Open Web Text)

Max Activating Token Index: 119

Text #9

Max Range: 4.5760. Min Range: -4.5760

Max Act: 4.1418. Min Act: -0.1700

Data Index: 8783703 (Open Web Text)

Max Activating Token Index: 121

Text #10

Max Range: 4.5760. Min Range: -4.5760

Max Act: 4.0796. Min Act: -0.1700

Data Index: 3741176 (Open Web Text)

Max Activating Token Index: 66

Text #11

Max Range: 4.5760. Min Range: -4.5760

Max Act: 4.1153. Min Act: -0.1700

Data Index: 168597 (Open Web Text)

Max Activating Token Index: 384

Text #12

Max Range: 4.5760. Min Range: -4.5760

Max Act: 4.1234. Min Act: -0.1700

Data Index: 2121943 (Open Web Text)

Max Activating Token Index: 509

Text #13

Max Range: 4.5760. Min Range: -4.5760

Max Act: 4.1418. Min Act: -0.1700

Data Index: 6813011 (Open Web Text)

Max Activating Token Index: 226

Text #14

Max Range: 4.5760. Min Range: -4.5760

Max Act: 4.1133. Min Act: -0.1700

Data Index: 8813334 (Open Web Text)

Max Activating Token Index: 597

Text #15

Max Range: 4.5760. Min Range: -4.5760

Max Act: 4.0742. Min Act: -0.1700

Data Index: 2129900 (Open Web Text)

Max Activating Token Index: 853

Text #16

Max Range: 4.5760. Min Range: -4.5760

Max Act: 4.0868. Min Act: -0.1700

Data Index: 4499743 (Open Web Text)

Max Activating Token Index: 55

Text #17

Max Range: 4.5760. Min Range: -4.5760

Max Act: 4.0896. Min Act: -0.1700

Data Index: 2038944 (Open Web Text)

Max Activating Token Index: 404

Text #18

Max Range: 4.5760. Min Range: -4.5760

Max Act: 4.0844. Min Act: -0.1700

Data Index: 1056463 (Open Web Text)

Max Activating Token Index: 35

Text #19

Max Range: 4.5760. Min Range: -4.5760

Max Act: 4.1041. Min Act: -0.1700

Data Index: 4508323 (Open Web Text)

Max Activating Token Index: 564