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

Dataset: Open Web Text

Neuron 2658 in Layer 1

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: 5.1196. Min Range: -5.1196

Max Act: 5.1196. Min Act: -0.1700

Data Index: 4004660 (Open Web Text)

Max Activating Token Index: 270

Text #1

Max Range: 5.1196. Min Range: -5.1196

Max Act: 5.0977. Min Act: -0.1700

Data Index: 8338584 (Open Web Text)

Max Activating Token Index: 638

Text #2

Max Range: 5.1196. Min Range: -5.1196

Max Act: 5.1084. Min Act: -0.1700

Data Index: 4156399 (Open Web Text)

Max Activating Token Index: 414

Text #3

Max Range: 5.1196. Min Range: -5.1196

Max Act: 5.0822. Min Act: -0.1700

Data Index: 7975767 (Open Web Text)

Max Activating Token Index: 53

Text #4

Max Range: 5.1196. Min Range: -5.1196

Max Act: 5.0742. Min Act: -0.1700

Data Index: 6237527 (Open Web Text)

Max Activating Token Index: 487

Text #5

Max Range: 5.1196. Min Range: -5.1196

Max Act: 5.0418. Min Act: -0.1700

Data Index: 3415380 (Open Web Text)

Max Activating Token Index: 211

Text #6

Max Range: 5.1196. Min Range: -5.1196

Max Act: 5.0002. Min Act: -0.1700

Data Index: 8159503 (Open Web Text)

Max Activating Token Index: 1022

Text #7

Max Range: 5.1196. Min Range: -5.1196

Max Act: 5.0336. Min Act: -0.1700

Data Index: 2747649 (Open Web Text)

Max Activating Token Index: 687

Text #8

Max Range: 5.1196. Min Range: -5.1196

Max Act: 4.9550. Min Act: -0.1700

Data Index: 8925 (Open Web Text)

Max Activating Token Index: 242

Text #9

Max Range: 5.1196. Min Range: -5.1196

Max Act: 4.9893. Min Act: -0.1700

Data Index: 7134504 (Open Web Text)

Max Activating Token Index: 648

Text #10

Max Range: 5.1196. Min Range: -5.1196

Max Act: 4.9897. Min Act: -0.1700

Data Index: 773307 (Open Web Text)

Max Activating Token Index: 600

Text #11

Max Range: 5.1196. Min Range: -5.1196

Max Act: 5.0006. Min Act: -0.1700

Data Index: 6629059 (Open Web Text)

Max Activating Token Index: 1008

Text #12

Max Range: 5.1196. Min Range: -5.1196

Max Act: 4.9728. Min Act: -0.1700

Data Index: 235365 (Open Web Text)

Max Activating Token Index: 675

Text #13

Max Range: 5.1196. Min Range: -5.1196

Max Act: 4.9812. Min Act: -0.1700

Data Index: 6481183 (Open Web Text)

Max Activating Token Index: 452

Text #14

Max Range: 5.1196. Min Range: -5.1196

Max Act: 4.9811. Min Act: -0.1700

Data Index: 5873491 (Open Web Text)

Max Activating Token Index: 308

Text #15

Max Range: 5.1196. Min Range: -5.1196

Max Act: 4.9726. Min Act: -0.1700

Data Index: 4892847 (Open Web Text)

Max Activating Token Index: 724

Text #16

Max Range: 5.1196. Min Range: -5.1196

Max Act: 4.9995. Min Act: -0.1700

Data Index: 1069605 (Open Web Text)

Max Activating Token Index: 473

Text #17

Max Range: 5.1196. Min Range: -5.1196

Max Act: 4.9535. Min Act: -0.1700

Data Index: 4456368 (Open Web Text)

Max Activating Token Index: 41

Text #18

Max Range: 5.1196. Min Range: -5.1196

Max Act: 4.9639. Min Act: -0.1700

Data Index: 928650 (Open Web Text)

Max Activating Token Index: 537

Text #19

Max Range: 5.1196. Min Range: -5.1196

Max Act: 5.0024. Min Act: -0.1700

Data Index: 4454348 (Open Web Text)

Max Activating Token Index: 456