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

Dataset: Open Web Text

Neuron 2877 in Layer 4

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: 2.9206. Min Range: -2.9206

Max Act: 2.9206. Min Act: -0.1700

Data Index: 4061592 (Open Web Text)

Max Activating Token Index: 119

Text #1

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.8619. Min Act: -0.1700

Data Index: 305608 (Open Web Text)

Max Activating Token Index: 718

Text #2

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.8627. Min Act: -0.1700

Data Index: 6260524 (Open Web Text)

Max Activating Token Index: 80

Text #3

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.8403. Min Act: -0.1700

Data Index: 1408364 (Open Web Text)

Max Activating Token Index: 124

Text #4

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.8414. Min Act: -0.1700

Data Index: 2196473 (Open Web Text)

Max Activating Token Index: 138

Text #5

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.8125. Min Act: -0.1700

Data Index: 2456981 (Open Web Text)

Max Activating Token Index: 412

Text #6

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.8287. Min Act: -0.1700

Data Index: 5000869 (Open Web Text)

Max Activating Token Index: 362

Text #7

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.8606. Min Act: -0.1700

Data Index: 3137667 (Open Web Text)

Max Activating Token Index: 589

Text #8

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.8034. Min Act: -0.1700

Data Index: 5380469 (Open Web Text)

Max Activating Token Index: 759

Text #9

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.7881. Min Act: -0.1700

Data Index: 2120568 (Open Web Text)

Max Activating Token Index: 578

Text #10

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.8225. Min Act: -0.1700

Data Index: 2021766 (Open Web Text)

Max Activating Token Index: 1001

Text #11

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.8020. Min Act: -0.1700

Data Index: 4977984 (Open Web Text)

Max Activating Token Index: 428

Text #12

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.7806. Min Act: -0.1700

Data Index: 2221583 (Open Web Text)

Max Activating Token Index: 813

Text #13

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.7829. Min Act: -0.1700

Data Index: 4210148 (Open Web Text)

Max Activating Token Index: 505

Text #14

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.7816. Min Act: -0.1700

Data Index: 6447060 (Open Web Text)

Max Activating Token Index: 517

Text #15

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.7626. Min Act: -0.1700

Data Index: 6250379 (Open Web Text)

Max Activating Token Index: 160

Text #16

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.7745. Min Act: -0.1700

Data Index: 116957 (Open Web Text)

Max Activating Token Index: 851

Text #17

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.7731. Min Act: -0.1700

Data Index: 4542744 (Open Web Text)

Max Activating Token Index: 721

Text #18

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.7875. Min Act: -0.1700

Data Index: 399390 (Open Web Text)

Max Activating Token Index: 15

Text #19

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.7606. Min Act: -0.1700

Data Index: 1624472 (Open Web Text)

Max Activating Token Index: 379