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

Dataset: Open Web Text

Neuron 2333 in Layer 3

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: 4.7212. Min Range: -4.7212

Max Act: 4.7212. Min Act: -0.1700

Data Index: 89948 (Open Web Text)

Max Activating Token Index: 583

Text #1

Max Range: 4.7212. Min Range: -4.7212

Max Act: 4.7033. Min Act: -0.1700

Data Index: 3409135 (Open Web Text)

Max Activating Token Index: 694

Text #2

Max Range: 4.7212. Min Range: -4.7212

Max Act: 4.6428. Min Act: -0.1700

Data Index: 89936 (Open Web Text)

Max Activating Token Index: 332

Text #3

Max Range: 4.7212. Min Range: -4.7212

Max Act: 4.6163. Min Act: -0.1700

Data Index: 2771822 (Open Web Text)

Max Activating Token Index: 910

Text #4

Max Range: 4.7212. Min Range: -4.7212

Max Act: 4.5984. Min Act: -0.1700

Data Index: 3745809 (Open Web Text)

Max Activating Token Index: 787

Text #5

Max Range: 4.7212. Min Range: -4.7212

Max Act: 4.5737. Min Act: -0.1700

Data Index: 8020261 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 4.7212. Min Range: -4.7212

Max Act: 4.5664. Min Act: -0.1700

Data Index: 5381826 (Open Web Text)

Max Activating Token Index: 179

Text #7

Max Range: 4.7212. Min Range: -4.7212

Max Act: 4.5777. Min Act: -0.1700

Data Index: 7755310 (Open Web Text)

Max Activating Token Index: 519

Text #8

Max Range: 4.7212. Min Range: -4.7212

Max Act: 4.5694. Min Act: -0.1700

Data Index: 3942619 (Open Web Text)

Max Activating Token Index: 811

Text #9

Max Range: 4.7212. Min Range: -4.7212

Max Act: 4.5232. Min Act: -0.1700

Data Index: 245255 (Open Web Text)

Max Activating Token Index: 971

Text #10

Max Range: 4.7212. Min Range: -4.7212

Max Act: 4.5242. Min Act: -0.1700

Data Index: 7156206 (Open Web Text)

Max Activating Token Index: 580

Text #11

Max Range: 4.7212. Min Range: -4.7212

Max Act: 4.5154. Min Act: -0.1700

Data Index: 3576108 (Open Web Text)

Max Activating Token Index: 978

Text #12

Max Range: 4.7212. Min Range: -4.7212

Max Act: 4.5217. Min Act: -0.1700

Data Index: 5655076 (Open Web Text)

Max Activating Token Index: 722

Text #13

Max Range: 4.7212. Min Range: -4.7212

Max Act: 4.5205. Min Act: -0.1700

Data Index: 7890303 (Open Web Text)

Max Activating Token Index: 1000

Text #14

Max Range: 4.7212. Min Range: -4.7212

Max Act: 4.5089. Min Act: -0.1700

Data Index: 994403 (Open Web Text)

Max Activating Token Index: 597

Text #15

Max Range: 4.7212. Min Range: -4.7212

Max Act: 4.5419. Min Act: -0.1700

Data Index: 2750603 (Open Web Text)

Max Activating Token Index: 516

Text #16

Max Range: 4.7212. Min Range: -4.7212

Max Act: 4.4884. Min Act: -0.1700

Data Index: 1580104 (Open Web Text)

Max Activating Token Index: 812

Text #17

Max Range: 4.7212. Min Range: -4.7212

Max Act: 4.4762. Min Act: -0.1700

Data Index: 1725370 (Open Web Text)

Max Activating Token Index: 17

Text #18

Max Range: 4.7212. Min Range: -4.7212

Max Act: 4.4715. Min Act: -0.1700

Data Index: 3635334 (Open Web Text)

Max Activating Token Index: 517

Text #19

Max Range: 4.7212. Min Range: -4.7212

Max Act: 4.4750. Min Act: -0.1700

Data Index: 602446 (Open Web Text)

Max Activating Token Index: 548