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

Dataset: Open Web Text

Neuron 1466 in Layer 4

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: 5.1358. Min Range: -5.1358

Max Act: 5.1358. Min Act: -0.1700

Data Index: 5141987 (Open Web Text)

Max Activating Token Index: 1014

Text #1

Max Range: 5.1358. Min Range: -5.1358

Max Act: 5.1264. Min Act: -0.1700

Data Index: 6208655 (Open Web Text)

Max Activating Token Index: 308

Text #2

Max Range: 5.1358. Min Range: -5.1358

Max Act: 5.0878. Min Act: -0.1700

Data Index: 7926143 (Open Web Text)

Max Activating Token Index: 408

Text #3

Max Range: 5.1358. Min Range: -5.1358

Max Act: 5.0790. Min Act: -0.1700

Data Index: 3006570 (Open Web Text)

Max Activating Token Index: 586

Text #4

Max Range: 5.1358. Min Range: -5.1358

Max Act: 5.0925. Min Act: -0.1700

Data Index: 489488 (Open Web Text)

Max Activating Token Index: 362

Text #5

Max Range: 5.1358. Min Range: -5.1358

Max Act: 5.0608. Min Act: -0.1700

Data Index: 7666092 (Open Web Text)

Max Activating Token Index: 770

Text #6

Max Range: 5.1358. Min Range: -5.1358

Max Act: 5.0345. Min Act: -0.1700

Data Index: 8734734 (Open Web Text)

Max Activating Token Index: 695

Text #7

Max Range: 5.1358. Min Range: -5.1358

Max Act: 5.0634. Min Act: -0.1700

Data Index: 5583409 (Open Web Text)

Max Activating Token Index: 412

Text #8

Max Range: 5.1358. Min Range: -5.1358

Max Act: 5.0340. Min Act: -0.1700

Data Index: 3775518 (Open Web Text)

Max Activating Token Index: 960

Text #9

Max Range: 5.1358. Min Range: -5.1358

Max Act: 5.0192. Min Act: -0.1700

Data Index: 6000650 (Open Web Text)

Max Activating Token Index: 840

Text #10

Max Range: 5.1358. Min Range: -5.1358

Max Act: 5.0178. Min Act: -0.1700

Data Index: 7304922 (Open Web Text)

Max Activating Token Index: 174

Text #11

Max Range: 5.1358. Min Range: -5.1358

Max Act: 4.9877. Min Act: -0.1700

Data Index: 7609605 (Open Web Text)

Max Activating Token Index: 490

Text #12

Max Range: 5.1358. Min Range: -5.1358

Max Act: 5.0266. Min Act: -0.1700

Data Index: 1595233 (Open Web Text)

Max Activating Token Index: 437

Text #13

Max Range: 5.1358. Min Range: -5.1358

Max Act: 4.9910. Min Act: -0.1700

Data Index: 2897051 (Open Web Text)

Max Activating Token Index: 813

Text #14

Max Range: 5.1358. Min Range: -5.1358

Max Act: 4.9749. Min Act: -0.1700

Data Index: 387827 (Open Web Text)

Max Activating Token Index: 919

Text #15

Max Range: 5.1358. Min Range: -5.1358

Max Act: 4.9939. Min Act: -0.1700

Data Index: 8310889 (Open Web Text)

Max Activating Token Index: 317

Text #16

Max Range: 5.1358. Min Range: -5.1358

Max Act: 4.9905. Min Act: -0.1700

Data Index: 436188 (Open Web Text)

Max Activating Token Index: 1019

Text #17

Max Range: 5.1358. Min Range: -5.1358

Max Act: 4.9423. Min Act: -0.1700

Data Index: 6136351 (Open Web Text)

Max Activating Token Index: 137

Text #18

Max Range: 5.1358. Min Range: -5.1358

Max Act: 4.9806. Min Act: -0.1700

Data Index: 2415607 (Open Web Text)

Max Activating Token Index: 695

Text #19

Max Range: 5.1358. Min Range: -5.1358

Max Act: 4.9739. Min Act: -0.1700

Data Index: 6385274 (Open Web Text)

Max Activating Token Index: 173