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

Dataset: Open Web Text

Neuron 469 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: 2.0566. Min Range: -2.0566

Max Act: 2.0566. Min Act: -0.1700

Data Index: 539237 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 2.0566. Min Range: -2.0566

Max Act: 2.0225. Min Act: -0.1699

Data Index: 3927583 (Open Web Text)

Max Activating Token Index: 17

Text #2

Max Range: 2.0566. Min Range: -2.0566

Max Act: 2.0070. Min Act: -0.1700

Data Index: 1544146 (Open Web Text)

Max Activating Token Index: 12

Text #3

Max Range: 2.0566. Min Range: -2.0566

Max Act: 2.0052. Min Act: -0.1700

Data Index: 2264816 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.9910. Min Act: -0.1689

Data Index: 8446607 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.9630. Min Act: -0.1699

Data Index: 1073612 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.9489. Min Act: -0.1700

Data Index: 5607750 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.9444. Min Act: -0.1700

Data Index: 799612 (Open Web Text)

Max Activating Token Index: 374

Text #8

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.9453. Min Act: -0.1698

Data Index: 7441054 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.9420. Min Act: -0.1697

Data Index: 5249782 (Open Web Text)

Max Activating Token Index: 15

Text #10

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.9318. Min Act: -0.1700

Data Index: 2184525 (Open Web Text)

Max Activating Token Index: 129

Text #11

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.9418. Min Act: -0.1700

Data Index: 8298157 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.9371. Min Act: -0.1700

Data Index: 7663622 (Open Web Text)

Max Activating Token Index: 103

Text #13

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.9348. Min Act: -0.1700

Data Index: 769797 (Open Web Text)

Max Activating Token Index: 410

Text #14

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.9295. Min Act: -0.1700

Data Index: 8235487 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.9305. Min Act: -0.1700

Data Index: 3474607 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.9295. Min Act: -0.1696

Data Index: 1377868 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.9260. Min Act: -0.1694

Data Index: 3139808 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.9276. Min Act: -0.1694

Data Index: 8200687 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.9287. Min Act: -0.1700

Data Index: 7027231 (Open Web Text)

Max Activating Token Index: 11