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

Dataset: Open Web Text

Neuron 2613 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: 1.3506. Min Range: -1.3506

Max Act: 1.3432. Min Act: -0.1700

Data Index: 2789159 (Open Web Text)

Max Activating Token Index: 556

Text #1

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.3506. Min Act: -0.1700

Data Index: 2170571 (Open Web Text)

Max Activating Token Index: 524

Text #2

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.3308. Min Act: -0.1699

Data Index: 3275557 (Open Web Text)

Max Activating Token Index: 521

Text #3

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.3158. Min Act: -0.1700

Data Index: 7544479 (Open Web Text)

Max Activating Token Index: 653

Text #4

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.3025. Min Act: -0.1700

Data Index: 5342415 (Open Web Text)

Max Activating Token Index: 616

Text #5

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.2993. Min Act: -0.1700

Data Index: 871654 (Open Web Text)

Max Activating Token Index: 646

Text #6

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.2849. Min Act: -0.1700

Data Index: 4807301 (Open Web Text)

Max Activating Token Index: 924

Text #7

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.2873. Min Act: -0.1700

Data Index: 1667693 (Open Web Text)

Max Activating Token Index: 962

Text #8

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.2918. Min Act: -0.1697

Data Index: 3390872 (Open Web Text)

Max Activating Token Index: 582

Text #9

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.2736. Min Act: -0.1700

Data Index: 7635683 (Open Web Text)

Max Activating Token Index: 1001

Text #10

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.2779. Min Act: -0.1700

Data Index: 763630 (Open Web Text)

Max Activating Token Index: 631

Text #11

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.2769. Min Act: -0.1698

Data Index: 2546219 (Open Web Text)

Max Activating Token Index: 576

Text #12

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.2742. Min Act: -0.1695

Data Index: 1342101 (Open Web Text)

Max Activating Token Index: 760

Text #13

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.2759. Min Act: -0.1700

Data Index: 721245 (Open Web Text)

Max Activating Token Index: 170

Text #14

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.2686. Min Act: -0.1700

Data Index: 7178926 (Open Web Text)

Max Activating Token Index: 552

Text #15

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.2679. Min Act: -0.1700

Data Index: 7606984 (Open Web Text)

Max Activating Token Index: 36

Text #16

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.2702. Min Act: -0.1653

Data Index: 1208319 (Open Web Text)

Max Activating Token Index: 591

Text #17

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.2622. Min Act: -0.1700

Data Index: 6783503 (Open Web Text)

Max Activating Token Index: 508

Text #18

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.2536. Min Act: -0.1690

Data Index: 529981 (Open Web Text)

Max Activating Token Index: 404

Text #19

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.2598. Min Act: -0.1700

Data Index: 6975293 (Open Web Text)

Max Activating Token Index: 600