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

Dataset: Open Web Text

Neuron 106 in Layer 0

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: 1.4511. Min Range: -1.4511

Max Act: 1.4469. Min Act: -0.1668

Data Index: 4368705 (Open Web Text)

Max Activating Token Index: 695

Text #1

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.4511. Min Act: -0.1645

Data Index: 6916410 (Open Web Text)

Max Activating Token Index: 339

Text #2

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.3993. Min Act: -0.1645

Data Index: 710428 (Open Web Text)

Max Activating Token Index: 310

Text #3

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.3755. Min Act: -0.1645

Data Index: 8497337 (Open Web Text)

Max Activating Token Index: 97

Text #4

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.3773. Min Act: -0.1645

Data Index: 5125467 (Open Web Text)

Max Activating Token Index: 482

Text #5

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.3645. Min Act: -0.1645

Data Index: 1498312 (Open Web Text)

Max Activating Token Index: 793

Text #6

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.3636. Min Act: -0.1645

Data Index: 4384178 (Open Web Text)

Max Activating Token Index: 98

Text #7

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.3716. Min Act: -0.1645

Data Index: 3059087 (Open Web Text)

Max Activating Token Index: 844

Text #8

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.3618. Min Act: -0.1645

Data Index: 4290714 (Open Web Text)

Max Activating Token Index: 559

Text #9

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.3564. Min Act: -0.1645

Data Index: 5444851 (Open Web Text)

Max Activating Token Index: 569

Text #10

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.3733. Min Act: -0.1645

Data Index: 42336 (Open Web Text)

Max Activating Token Index: 921

Text #11

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.3517. Min Act: -0.1699

Data Index: 5028895 (Open Web Text)

Max Activating Token Index: 387

Text #12

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.3591. Min Act: -0.1645

Data Index: 7998078 (Open Web Text)

Max Activating Token Index: 866

Text #13

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.3560. Min Act: -0.1645

Data Index: 7952674 (Open Web Text)

Max Activating Token Index: 858

Text #14

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.3538. Min Act: -0.1645

Data Index: 4512723 (Open Web Text)

Max Activating Token Index: 754

Text #15

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.3304. Min Act: -0.1682

Data Index: 4511200 (Open Web Text)

Max Activating Token Index: 939

Text #16

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.3522. Min Act: -0.1645

Data Index: 5638266 (Open Web Text)

Max Activating Token Index: 71

Text #17

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.3540. Min Act: -0.1645

Data Index: 1138287 (Open Web Text)

Max Activating Token Index: 827

Text #18

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.3434. Min Act: -0.1645

Data Index: 4368707 (Open Web Text)

Max Activating Token Index: 186

Text #19

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.3379. Min Act: -0.1698

Data Index: 2563088 (Open Web Text)

Max Activating Token Index: 298