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

Dataset: Open Web Text

Neuron 1304 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: 1.3291. Min Range: -1.3291

Max Act: 1.3287. Min Act: -0.1700

Data Index: 2709380 (Open Web Text)

Max Activating Token Index: 336

Text #1

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.3291. Min Act: -0.1699

Data Index: 4255478 (Open Web Text)

Max Activating Token Index: 938

Text #2

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.3053. Min Act: -0.1700

Data Index: 1703321 (Open Web Text)

Max Activating Token Index: 495

Text #3

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.3090. Min Act: -0.1700

Data Index: 629255 (Open Web Text)

Max Activating Token Index: 1021

Text #4

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.3001. Min Act: -0.1700

Data Index: 4255480 (Open Web Text)

Max Activating Token Index: 525

Text #5

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.2991. Min Act: -0.1700

Data Index: 4584904 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.2898. Min Act: -0.1700

Data Index: 3416775 (Open Web Text)

Max Activating Token Index: 633

Text #7

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.2933. Min Act: -0.1700

Data Index: 4255489 (Open Web Text)

Max Activating Token Index: 429

Text #8

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.2979. Min Act: -0.1700

Data Index: 7924867 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.2899. Min Act: -0.1700

Data Index: 8544775 (Open Web Text)

Max Activating Token Index: 395

Text #10

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.2812. Min Act: -0.1700

Data Index: 311814 (Open Web Text)

Max Activating Token Index: 582

Text #11

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.2760. Min Act: -0.1700

Data Index: 5514424 (Open Web Text)

Max Activating Token Index: 550

Text #12

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.2871. Min Act: -0.1700

Data Index: 4613270 (Open Web Text)

Max Activating Token Index: 46

Text #13

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.2837. Min Act: -0.1700

Data Index: 3561830 (Open Web Text)

Max Activating Token Index: 889

Text #14

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.2831. Min Act: -0.1697

Data Index: 4255490 (Open Web Text)

Max Activating Token Index: 829

Text #15

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.2720. Min Act: -0.1700

Data Index: 937416 (Open Web Text)

Max Activating Token Index: 393

Text #16

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.2784. Min Act: -0.1700

Data Index: 73358 (Open Web Text)

Max Activating Token Index: 1005

Text #17

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.2755. Min Act: -0.1700

Data Index: 1423352 (Open Web Text)

Max Activating Token Index: 412

Text #18

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.2704. Min Act: -0.1700

Data Index: 7240554 (Open Web Text)

Max Activating Token Index: 321

Text #19

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.2775. Min Act: -0.1699

Data Index: 561885 (Open Web Text)

Max Activating Token Index: 129