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

Dataset: Open Web Text

Neuron 1647 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: 2.6161. Min Range: -2.6161

Max Act: 2.6161. Min Act: -0.1700

Data Index: 7260869 (Open Web Text)

Max Activating Token Index: 420

Text #1

Max Range: 2.6161. Min Range: -2.6161

Max Act: 2.5624. Min Act: -0.1700

Data Index: 4831023 (Open Web Text)

Max Activating Token Index: 743

Text #2

Max Range: 2.6161. Min Range: -2.6161

Max Act: 2.5121. Min Act: -0.1700

Data Index: 610205 (Open Web Text)

Max Activating Token Index: 916

Text #3

Max Range: 2.6161. Min Range: -2.6161

Max Act: 2.4778. Min Act: -0.1700

Data Index: 58937 (Open Web Text)

Max Activating Token Index: 395

Text #4

Max Range: 2.6161. Min Range: -2.6161

Max Act: 2.5160. Min Act: -0.1700

Data Index: 3673482 (Open Web Text)

Max Activating Token Index: 512

Text #5

Max Range: 2.6161. Min Range: -2.6161

Max Act: 2.5181. Min Act: -0.1700

Data Index: 4669595 (Open Web Text)

Max Activating Token Index: 372

Text #6

Max Range: 2.6161. Min Range: -2.6161

Max Act: 2.4976. Min Act: -0.1700

Data Index: 7184949 (Open Web Text)

Max Activating Token Index: 861

Text #7

Max Range: 2.6161. Min Range: -2.6161

Max Act: 2.4967. Min Act: -0.1700

Data Index: 7934330 (Open Web Text)

Max Activating Token Index: 257

Text #8

Max Range: 2.6161. Min Range: -2.6161

Max Act: 2.4691. Min Act: -0.1700

Data Index: 1768855 (Open Web Text)

Max Activating Token Index: 461

Text #9

Max Range: 2.6161. Min Range: -2.6161

Max Act: 2.4685. Min Act: -0.1700

Data Index: 1641359 (Open Web Text)

Max Activating Token Index: 877

Text #10

Max Range: 2.6161. Min Range: -2.6161

Max Act: 2.4472. Min Act: -0.1700

Data Index: 6728651 (Open Web Text)

Max Activating Token Index: 485

Text #11

Max Range: 2.6161. Min Range: -2.6161

Max Act: 2.4486. Min Act: -0.1700

Data Index: 5446398 (Open Web Text)

Max Activating Token Index: 279

Text #12

Max Range: 2.6161. Min Range: -2.6161

Max Act: 2.4629. Min Act: -0.1700

Data Index: 3092258 (Open Web Text)

Max Activating Token Index: 802

Text #13

Max Range: 2.6161. Min Range: -2.6161

Max Act: 2.4622. Min Act: -0.1700

Data Index: 803143 (Open Web Text)

Max Activating Token Index: 86

Text #14

Max Range: 2.6161. Min Range: -2.6161

Max Act: 2.4647. Min Act: -0.1700

Data Index: 5734940 (Open Web Text)

Max Activating Token Index: 635

Text #15

Max Range: 2.6161. Min Range: -2.6161

Max Act: 2.4153. Min Act: -0.1700

Data Index: 8029623 (Open Web Text)

Max Activating Token Index: 636

Text #16

Max Range: 2.6161. Min Range: -2.6161

Max Act: 2.4777. Min Act: -0.1700

Data Index: 8612498 (Open Web Text)

Max Activating Token Index: 870

Text #17

Max Range: 2.6161. Min Range: -2.6161

Max Act: 2.4533. Min Act: -0.1700

Data Index: 6457796 (Open Web Text)

Max Activating Token Index: 502

Text #18

Max Range: 2.6161. Min Range: -2.6161

Max Act: 2.4438. Min Act: -0.1700

Data Index: 2291633 (Open Web Text)

Max Activating Token Index: 590

Text #19

Max Range: 2.6161. Min Range: -2.6161

Max Act: 2.4031. Min Act: -0.1700

Data Index: 6753910 (Open Web Text)

Max Activating Token Index: 689