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

Dataset: Open Web Text

Neuron 463 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: 2.9219. Min Range: -2.9219

Max Act: 2.9022. Min Act: -0.1700

Data Index: 7857242 (Open Web Text)

Max Activating Token Index: 886

Text #1

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.9219. Min Act: -0.1700

Data Index: 1114461 (Open Web Text)

Max Activating Token Index: 359

Text #2

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.8912. Min Act: -0.1700

Data Index: 4262334 (Open Web Text)

Max Activating Token Index: 927

Text #3

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.8538. Min Act: -0.1700

Data Index: 8450605 (Open Web Text)

Max Activating Token Index: 1003

Text #4

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.8918. Min Act: -0.1700

Data Index: 5546751 (Open Web Text)

Max Activating Token Index: 469

Text #5

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.8428. Min Act: -0.1700

Data Index: 5014649 (Open Web Text)

Max Activating Token Index: 215

Text #6

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.8457. Min Act: -0.1700

Data Index: 3222969 (Open Web Text)

Max Activating Token Index: 60

Text #7

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.8284. Min Act: -0.1700

Data Index: 8093787 (Open Web Text)

Max Activating Token Index: 664

Text #8

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.8261. Min Act: -0.1700

Data Index: 8379426 (Open Web Text)

Max Activating Token Index: 798

Text #9

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.8241. Min Act: -0.1700

Data Index: 951170 (Open Web Text)

Max Activating Token Index: 782

Text #10

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.8219. Min Act: -0.1700

Data Index: 8439220 (Open Web Text)

Max Activating Token Index: 43

Text #11

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.8090. Min Act: -0.1700

Data Index: 3213940 (Open Web Text)

Max Activating Token Index: 207

Text #12

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.8320. Min Act: -0.1700

Data Index: 5058330 (Open Web Text)

Max Activating Token Index: 361

Text #13

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.8054. Min Act: -0.1700

Data Index: 8361863 (Open Web Text)

Max Activating Token Index: 440

Text #14

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.8151. Min Act: -0.1700

Data Index: 4222316 (Open Web Text)

Max Activating Token Index: 506

Text #15

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.8194. Min Act: -0.1700

Data Index: 2360181 (Open Web Text)

Max Activating Token Index: 572

Text #16

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.8001. Min Act: -0.1700

Data Index: 1497943 (Open Web Text)

Max Activating Token Index: 691

Text #17

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.8026. Min Act: -0.1700

Data Index: 6395983 (Open Web Text)

Max Activating Token Index: 100

Text #18

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.7989. Min Act: -0.1700

Data Index: 3588821 (Open Web Text)

Max Activating Token Index: 136

Text #19

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.7925. Min Act: -0.1700

Data Index: 8024387 (Open Web Text)

Max Activating Token Index: 507