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

Dataset: Open Web Text

Neuron 793 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: 2.0341. Min Range: -2.0341

Max Act: 2.0341. Min Act: -0.1700

Data Index: 786955 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 2.0341. Min Range: -2.0341

Max Act: 1.9801. Min Act: -0.1700

Data Index: 6652768 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 2.0341. Min Range: -2.0341

Max Act: 1.9768. Min Act: -0.1700

Data Index: 4241234 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 2.0341. Min Range: -2.0341

Max Act: 1.9621. Min Act: -0.1700

Data Index: 7231548 (Open Web Text)

Max Activating Token Index: 12

Text #4

Max Range: 2.0341. Min Range: -2.0341

Max Act: 1.9533. Min Act: -0.1700

Data Index: 7474226 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 2.0341. Min Range: -2.0341

Max Act: 1.9610. Min Act: -0.1700

Data Index: 3633545 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.0341. Min Range: -2.0341

Max Act: 1.9709. Min Act: -0.1700

Data Index: 4741531 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 2.0341. Min Range: -2.0341

Max Act: 1.9584. Min Act: -0.1700

Data Index: 8304426 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 2.0341. Min Range: -2.0341

Max Act: 1.9351. Min Act: -0.1700

Data Index: 5396608 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 2.0341. Min Range: -2.0341

Max Act: 1.9488. Min Act: -0.1700

Data Index: 7074984 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 2.0341. Min Range: -2.0341

Max Act: 1.9398. Min Act: -0.1700

Data Index: 558185 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 2.0341. Min Range: -2.0341

Max Act: 1.9325. Min Act: -0.1700

Data Index: 2895692 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 2.0341. Min Range: -2.0341

Max Act: 1.9247. Min Act: -0.1700

Data Index: 1044439 (Open Web Text)

Max Activating Token Index: 229

Text #13

Max Range: 2.0341. Min Range: -2.0341

Max Act: 1.9086. Min Act: -0.1700

Data Index: 2369465 (Open Web Text)

Max Activating Token Index: 20

Text #14

Max Range: 2.0341. Min Range: -2.0341

Max Act: 1.9040. Min Act: -0.1700

Data Index: 3403633 (Open Web Text)

Max Activating Token Index: 404

Text #15

Max Range: 2.0341. Min Range: -2.0341

Max Act: 1.9086. Min Act: -0.1700

Data Index: 575618 (Open Web Text)

Max Activating Token Index: 17

Text #16

Max Range: 2.0341. Min Range: -2.0341

Max Act: 1.9129. Min Act: -0.1700

Data Index: 6622273 (Open Web Text)

Max Activating Token Index: 509

Text #17

Max Range: 2.0341. Min Range: -2.0341

Max Act: 1.9108. Min Act: -0.1700

Data Index: 6277362 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 2.0341. Min Range: -2.0341

Max Act: 1.9204. Min Act: -0.1700

Data Index: 5911103 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 2.0341. Min Range: -2.0341

Max Act: 1.9175. Min Act: -0.1700

Data Index: 5704927 (Open Web Text)

Max Activating Token Index: 5