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

Dataset: Open Web Text

Neuron 2438 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: 1.9065. Min Range: -1.9065

Max Act: 1.9065. Min Act: -0.1700

Data Index: 6261171 (Open Web Text)

Max Activating Token Index: 557

Text #1

Max Range: 1.9065. Min Range: -1.9065

Max Act: 1.8588. Min Act: -0.1700

Data Index: 1335531 (Open Web Text)

Max Activating Token Index: 560

Text #2

Max Range: 1.9065. Min Range: -1.9065

Max Act: 1.8342. Min Act: -0.1700

Data Index: 759585 (Open Web Text)

Max Activating Token Index: 386

Text #3

Max Range: 1.9065. Min Range: -1.9065

Max Act: 1.8299. Min Act: -0.1700

Data Index: 8620492 (Open Web Text)

Max Activating Token Index: 399

Text #4

Max Range: 1.9065. Min Range: -1.9065

Max Act: 1.8138. Min Act: -0.1700

Data Index: 1335542 (Open Web Text)

Max Activating Token Index: 651

Text #5

Max Range: 1.9065. Min Range: -1.9065

Max Act: 1.7878. Min Act: -0.1700

Data Index: 1339890 (Open Web Text)

Max Activating Token Index: 587

Text #6

Max Range: 1.9065. Min Range: -1.9065

Max Act: 1.7780. Min Act: -0.1700

Data Index: 3906676 (Open Web Text)

Max Activating Token Index: 1009

Text #7

Max Range: 1.9065. Min Range: -1.9065

Max Act: 1.7786. Min Act: -0.1700

Data Index: 3717941 (Open Web Text)

Max Activating Token Index: 472

Text #8

Max Range: 1.9065. Min Range: -1.9065

Max Act: 1.7764. Min Act: -0.1700

Data Index: 860625 (Open Web Text)

Max Activating Token Index: 487

Text #9

Max Range: 1.9065. Min Range: -1.9065

Max Act: 1.7664. Min Act: -0.1700

Data Index: 4720586 (Open Web Text)

Max Activating Token Index: 727

Text #10

Max Range: 1.9065. Min Range: -1.9065

Max Act: 1.7544. Min Act: -0.1700

Data Index: 2752380 (Open Web Text)

Max Activating Token Index: 389

Text #11

Max Range: 1.9065. Min Range: -1.9065

Max Act: 1.7566. Min Act: -0.1700

Data Index: 3891886 (Open Web Text)

Max Activating Token Index: 72

Text #12

Max Range: 1.9065. Min Range: -1.9065

Max Act: 1.7556. Min Act: -0.1700

Data Index: 2439018 (Open Web Text)

Max Activating Token Index: 689

Text #13

Max Range: 1.9065. Min Range: -1.9065

Max Act: 1.7574. Min Act: -0.1700

Data Index: 6411665 (Open Web Text)

Max Activating Token Index: 510

Text #14

Max Range: 1.9065. Min Range: -1.9065

Max Act: 1.7579. Min Act: -0.1700

Data Index: 74411 (Open Web Text)

Max Activating Token Index: 127

Text #15

Max Range: 1.9065. Min Range: -1.9065

Max Act: 1.7623. Min Act: -0.1700

Data Index: 1029653 (Open Web Text)

Max Activating Token Index: 591

Text #16

Max Range: 1.9065. Min Range: -1.9065

Max Act: 1.7529. Min Act: -0.1700

Data Index: 1601874 (Open Web Text)

Max Activating Token Index: 439

Text #17

Max Range: 1.9065. Min Range: -1.9065

Max Act: 1.7523. Min Act: -0.1700

Data Index: 160201 (Open Web Text)

Max Activating Token Index: 505

Text #18

Max Range: 1.9065. Min Range: -1.9065

Max Act: 1.7452. Min Act: -0.1700

Data Index: 6352034 (Open Web Text)

Max Activating Token Index: 902

Text #19

Max Range: 1.9065. Min Range: -1.9065

Max Act: 1.7480. Min Act: -0.1699

Data Index: 6669957 (Open Web Text)

Max Activating Token Index: 107