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

Dataset: Open Web Text

Neuron 114 in Layer 3

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: 4.5534. Min Range: -4.5534

Max Act: 4.5534. Min Act: -0.1700

Data Index: 110922 (Open Web Text)

Max Activating Token Index: 31

Text #1

Max Range: 4.5534. Min Range: -4.5534

Max Act: 4.1943. Min Act: -0.1700

Data Index: 2417465 (Open Web Text)

Max Activating Token Index: 69

Text #2

Max Range: 4.5534. Min Range: -4.5534

Max Act: 4.1309. Min Act: -0.1700

Data Index: 5936457 (Open Web Text)

Max Activating Token Index: 1007

Text #3

Max Range: 4.5534. Min Range: -4.5534

Max Act: 4.0910. Min Act: -0.1700

Data Index: 3401662 (Open Web Text)

Max Activating Token Index: 99

Text #4

Max Range: 4.5534. Min Range: -4.5534

Max Act: 4.0704. Min Act: -0.1700

Data Index: 4118706 (Open Web Text)

Max Activating Token Index: 690

Text #5

Max Range: 4.5534. Min Range: -4.5534

Max Act: 4.0505. Min Act: -0.1700

Data Index: 7028721 (Open Web Text)

Max Activating Token Index: 274

Text #6

Max Range: 4.5534. Min Range: -4.5534

Max Act: 4.0548. Min Act: -0.1700

Data Index: 6160649 (Open Web Text)

Max Activating Token Index: 319

Text #7

Max Range: 4.5534. Min Range: -4.5534

Max Act: 4.0338. Min Act: -0.1700

Data Index: 1962446 (Open Web Text)

Max Activating Token Index: 355

Text #8

Max Range: 4.5534. Min Range: -4.5534

Max Act: 4.0620. Min Act: -0.1700

Data Index: 6292520 (Open Web Text)

Max Activating Token Index: 715

Text #9

Max Range: 4.5534. Min Range: -4.5534

Max Act: 4.0052. Min Act: -0.1700

Data Index: 8109886 (Open Web Text)

Max Activating Token Index: 361

Text #10

Max Range: 4.5534. Min Range: -4.5534

Max Act: 4.0457. Min Act: -0.1700

Data Index: 2955064 (Open Web Text)

Max Activating Token Index: 896

Text #11

Max Range: 4.5534. Min Range: -4.5534

Max Act: 4.0405. Min Act: -0.1700

Data Index: 6296871 (Open Web Text)

Max Activating Token Index: 787

Text #12

Max Range: 4.5534. Min Range: -4.5534

Max Act: 3.9727. Min Act: -0.1700

Data Index: 6124051 (Open Web Text)

Max Activating Token Index: 682

Text #13

Max Range: 4.5534. Min Range: -4.5534

Max Act: 3.9893. Min Act: -0.1700

Data Index: 5797693 (Open Web Text)

Max Activating Token Index: 643

Text #14

Max Range: 4.5534. Min Range: -4.5534

Max Act: 3.9824. Min Act: -0.1700

Data Index: 6728737 (Open Web Text)

Max Activating Token Index: 40

Text #15

Max Range: 4.5534. Min Range: -4.5534

Max Act: 3.9773. Min Act: -0.1700

Data Index: 5489432 (Open Web Text)

Max Activating Token Index: 714

Text #16

Max Range: 4.5534. Min Range: -4.5534

Max Act: 3.9910. Min Act: -0.1700

Data Index: 1792907 (Open Web Text)

Max Activating Token Index: 161

Text #17

Max Range: 4.5534. Min Range: -4.5534

Max Act: 3.9661. Min Act: -0.1700

Data Index: 3293158 (Open Web Text)

Max Activating Token Index: 776

Text #18

Max Range: 4.5534. Min Range: -4.5534

Max Act: 3.9461. Min Act: -0.1700

Data Index: 5047837 (Open Web Text)

Max Activating Token Index: 537

Text #19

Max Range: 4.5534. Min Range: -4.5534

Max Act: 3.9802. Min Act: -0.1700

Data Index: 2656115 (Open Web Text)

Max Activating Token Index: 896