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

Dataset: Open Web Text

Neuron 1856 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: 6.8005. Min Range: -6.8005

Max Act: 6.7503. Min Act: -0.1700

Data Index: 1575211 (Open Web Text)

Max Activating Token Index: 1004

Text #1

Max Range: 6.8005. Min Range: -6.8005

Max Act: 6.7937. Min Act: -0.1700

Data Index: 3155728 (Open Web Text)

Max Activating Token Index: 616

Text #2

Max Range: 6.8005. Min Range: -6.8005

Max Act: 6.8005. Min Act: -0.1700

Data Index: 8565983 (Open Web Text)

Max Activating Token Index: 559

Text #3

Max Range: 6.8005. Min Range: -6.8005

Max Act: 6.6527. Min Act: -0.1700

Data Index: 6872903 (Open Web Text)

Max Activating Token Index: 652

Text #4

Max Range: 6.8005. Min Range: -6.8005

Max Act: 6.6536. Min Act: -0.1697

Data Index: 8299698 (Open Web Text)

Max Activating Token Index: 534

Text #5

Max Range: 6.8005. Min Range: -6.8005

Max Act: 6.3011. Min Act: -0.1700

Data Index: 3065866 (Open Web Text)

Max Activating Token Index: 493

Text #6

Max Range: 6.8005. Min Range: -6.8005

Max Act: 6.0913. Min Act: -0.1700

Data Index: 8007188 (Open Web Text)

Max Activating Token Index: 262

Text #7

Max Range: 6.8005. Min Range: -6.8005

Max Act: 6.1239. Min Act: -0.1694

Data Index: 4521762 (Open Web Text)

Max Activating Token Index: 434

Text #8

Max Range: 6.8005. Min Range: -6.8005

Max Act: 6.1839. Min Act: -0.1698

Data Index: 7298869 (Open Web Text)

Max Activating Token Index: 943

Text #9

Max Range: 6.8005. Min Range: -6.8005

Max Act: 5.9798. Min Act: -0.1693

Data Index: 5443689 (Open Web Text)

Max Activating Token Index: 716

Text #10

Max Range: 6.8005. Min Range: -6.8005

Max Act: 6.0734. Min Act: -0.1691

Data Index: 5867472 (Open Web Text)

Max Activating Token Index: 518

Text #11

Max Range: 6.8005. Min Range: -6.8005

Max Act: 6.0399. Min Act: -0.1700

Data Index: 6153411 (Open Web Text)

Max Activating Token Index: 181

Text #12

Max Range: 6.8005. Min Range: -6.8005

Max Act: 6.1167. Min Act: -0.1700

Data Index: 8007187 (Open Web Text)

Max Activating Token Index: 577

Text #13

Max Range: 6.8005. Min Range: -6.8005

Max Act: 6.0370. Min Act: -0.1700

Data Index: 6964156 (Open Web Text)

Max Activating Token Index: 807

Text #14

Max Range: 6.8005. Min Range: -6.8005

Max Act: 5.9739. Min Act: -0.1700

Data Index: 1678191 (Open Web Text)

Max Activating Token Index: 225

Text #15

Max Range: 6.8005. Min Range: -6.8005

Max Act: 5.8969. Min Act: -0.1700

Data Index: 2402810 (Open Web Text)

Max Activating Token Index: 347

Text #16

Max Range: 6.8005. Min Range: -6.8005

Max Act: 5.9274. Min Act: -0.1700

Data Index: 3934598 (Open Web Text)

Max Activating Token Index: 404

Text #17

Max Range: 6.8005. Min Range: -6.8005

Max Act: 5.8944. Min Act: -0.1699

Data Index: 4436225 (Open Web Text)

Max Activating Token Index: 335

Text #18

Max Range: 6.8005. Min Range: -6.8005

Max Act: 5.9725. Min Act: -0.1700

Data Index: 2222608 (Open Web Text)

Max Activating Token Index: 975

Text #19

Max Range: 6.8005. Min Range: -6.8005

Max Act: 5.8852. Min Act: -0.1700

Data Index: 1139294 (Open Web Text)

Max Activating Token Index: 992