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

Dataset: Open Web Text

Neuron 2585 in Layer 4

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: 4.4170. Min Range: -4.4170

Max Act: 4.4170. Min Act: -0.1700

Data Index: 6027166 (Open Web Text)

Max Activating Token Index: 250

Text #1

Max Range: 4.4170. Min Range: -4.4170

Max Act: 4.2658. Min Act: -0.1700

Data Index: 5041592 (Open Web Text)

Max Activating Token Index: 771

Text #2

Max Range: 4.4170. Min Range: -4.4170

Max Act: 4.2477. Min Act: -0.1700

Data Index: 567759 (Open Web Text)

Max Activating Token Index: 590

Text #3

Max Range: 4.4170. Min Range: -4.4170

Max Act: 4.2235. Min Act: -0.1700

Data Index: 8316083 (Open Web Text)

Max Activating Token Index: 76

Text #4

Max Range: 4.4170. Min Range: -4.4170

Max Act: 4.2513. Min Act: -0.1700

Data Index: 2243258 (Open Web Text)

Max Activating Token Index: 345

Text #5

Max Range: 4.4170. Min Range: -4.4170

Max Act: 4.2359. Min Act: -0.1700

Data Index: 728638 (Open Web Text)

Max Activating Token Index: 1014

Text #6

Max Range: 4.4170. Min Range: -4.4170

Max Act: 4.2025. Min Act: -0.1700

Data Index: 5123516 (Open Web Text)

Max Activating Token Index: 53

Text #7

Max Range: 4.4170. Min Range: -4.4170

Max Act: 4.2039. Min Act: -0.1700

Data Index: 8559401 (Open Web Text)

Max Activating Token Index: 387

Text #8

Max Range: 4.4170. Min Range: -4.4170

Max Act: 4.1964. Min Act: -0.1700

Data Index: 7111879 (Open Web Text)

Max Activating Token Index: 278

Text #9

Max Range: 4.4170. Min Range: -4.4170

Max Act: 4.2014. Min Act: -0.1700

Data Index: 7220680 (Open Web Text)

Max Activating Token Index: 682

Text #10

Max Range: 4.4170. Min Range: -4.4170

Max Act: 4.1730. Min Act: -0.1700

Data Index: 5367333 (Open Web Text)

Max Activating Token Index: 1007

Text #11

Max Range: 4.4170. Min Range: -4.4170

Max Act: 4.1934. Min Act: -0.1700

Data Index: 8121964 (Open Web Text)

Max Activating Token Index: 849

Text #12

Max Range: 4.4170. Min Range: -4.4170

Max Act: 4.1326. Min Act: -0.1700

Data Index: 7522880 (Open Web Text)

Max Activating Token Index: 102

Text #13

Max Range: 4.4170. Min Range: -4.4170

Max Act: 4.1500. Min Act: -0.1700

Data Index: 4284469 (Open Web Text)

Max Activating Token Index: 716

Text #14

Max Range: 4.4170. Min Range: -4.4170

Max Act: 4.1463. Min Act: -0.1700

Data Index: 1168724 (Open Web Text)

Max Activating Token Index: 251

Text #15

Max Range: 4.4170. Min Range: -4.4170

Max Act: 4.1216. Min Act: -0.1700

Data Index: 1743441 (Open Web Text)

Max Activating Token Index: 47

Text #16

Max Range: 4.4170. Min Range: -4.4170

Max Act: 4.0972. Min Act: -0.1700

Data Index: 6808316 (Open Web Text)

Max Activating Token Index: 759

Text #17

Max Range: 4.4170. Min Range: -4.4170

Max Act: 4.1029. Min Act: -0.1700

Data Index: 6441739 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 4.4170. Min Range: -4.4170

Max Act: 4.0772. Min Act: -0.1700

Data Index: 7688795 (Open Web Text)

Max Activating Token Index: 267

Text #19

Max Range: 4.4170. Min Range: -4.4170

Max Act: 4.0705. Min Act: -0.1700

Data Index: 7885239 (Open Web Text)

Max Activating Token Index: 150