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

Dataset: Open Web Text

Neuron 627 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: 5.5388. Min Range: -5.5388

Max Act: 5.5388. Min Act: -0.1700

Data Index: 1231336 (Open Web Text)

Max Activating Token Index: 533

Text #1

Max Range: 5.5388. Min Range: -5.5388

Max Act: 5.4856. Min Act: -0.1700

Data Index: 3937167 (Open Web Text)

Max Activating Token Index: 526

Text #2

Max Range: 5.5388. Min Range: -5.5388

Max Act: 5.4068. Min Act: -0.1700

Data Index: 1709650 (Open Web Text)

Max Activating Token Index: 405

Text #3

Max Range: 5.5388. Min Range: -5.5388

Max Act: 5.3738. Min Act: -0.1700

Data Index: 3187892 (Open Web Text)

Max Activating Token Index: 281

Text #4

Max Range: 5.5388. Min Range: -5.5388

Max Act: 5.3270. Min Act: -0.1700

Data Index: 7582699 (Open Web Text)

Max Activating Token Index: 337

Text #5

Max Range: 5.5388. Min Range: -5.5388

Max Act: 5.2582. Min Act: -0.1700

Data Index: 6399616 (Open Web Text)

Max Activating Token Index: 353

Text #6

Max Range: 5.5388. Min Range: -5.5388

Max Act: 5.2809. Min Act: -0.1700

Data Index: 3998035 (Open Web Text)

Max Activating Token Index: 305

Text #7

Max Range: 5.5388. Min Range: -5.5388

Max Act: 5.2897. Min Act: -0.1700

Data Index: 554779 (Open Web Text)

Max Activating Token Index: 143

Text #8

Max Range: 5.5388. Min Range: -5.5388

Max Act: 5.2735. Min Act: -0.1700

Data Index: 2434988 (Open Web Text)

Max Activating Token Index: 376

Text #9

Max Range: 5.5388. Min Range: -5.5388

Max Act: 5.2510. Min Act: -0.1700

Data Index: 5652004 (Open Web Text)

Max Activating Token Index: 507

Text #10

Max Range: 5.5388. Min Range: -5.5388

Max Act: 5.2626. Min Act: -0.1700

Data Index: 1873511 (Open Web Text)

Max Activating Token Index: 222

Text #11

Max Range: 5.5388. Min Range: -5.5388

Max Act: 5.2352. Min Act: -0.1700

Data Index: 8024249 (Open Web Text)

Max Activating Token Index: 479

Text #12

Max Range: 5.5388. Min Range: -5.5388

Max Act: 5.2274. Min Act: -0.1700

Data Index: 607043 (Open Web Text)

Max Activating Token Index: 461

Text #13

Max Range: 5.5388. Min Range: -5.5388

Max Act: 5.2640. Min Act: -0.1700

Data Index: 3866440 (Open Web Text)

Max Activating Token Index: 340

Text #14

Max Range: 5.5388. Min Range: -5.5388

Max Act: 5.2416. Min Act: -0.1700

Data Index: 5194181 (Open Web Text)

Max Activating Token Index: 381

Text #15

Max Range: 5.5388. Min Range: -5.5388

Max Act: 5.2435. Min Act: -0.1700

Data Index: 5186565 (Open Web Text)

Max Activating Token Index: 414

Text #16

Max Range: 5.5388. Min Range: -5.5388

Max Act: 5.2648. Min Act: -0.1700

Data Index: 3444988 (Open Web Text)

Max Activating Token Index: 126

Text #17

Max Range: 5.5388. Min Range: -5.5388

Max Act: 5.2609. Min Act: -0.1700

Data Index: 7306425 (Open Web Text)

Max Activating Token Index: 63

Text #18

Max Range: 5.5388. Min Range: -5.5388

Max Act: 5.2584. Min Act: -0.1700

Data Index: 6718353 (Open Web Text)

Max Activating Token Index: 258

Text #19

Max Range: 5.5388. Min Range: -5.5388

Max Act: 5.2479. Min Act: -0.1700

Data Index: 6568938 (Open Web Text)

Max Activating Token Index: 144