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

Dataset: Open Web Text

Neuron 2488 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: 4.8530. Min Range: -4.8530

Max Act: 4.8530. Min Act: -0.1700

Data Index: 2268390 (Open Web Text)

Max Activating Token Index: 590

Text #1

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.8083. Min Act: -0.1700

Data Index: 6245950 (Open Web Text)

Max Activating Token Index: 578

Text #2

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.7273. Min Act: -0.1700

Data Index: 5479016 (Open Web Text)

Max Activating Token Index: 531

Text #3

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.7176. Min Act: -0.1700

Data Index: 4665364 (Open Web Text)

Max Activating Token Index: 693

Text #4

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.7316. Min Act: -0.1700

Data Index: 7551430 (Open Web Text)

Max Activating Token Index: 100

Text #5

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.7126. Min Act: -0.1700

Data Index: 5448241 (Open Web Text)

Max Activating Token Index: 462

Text #6

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.7260. Min Act: -0.1700

Data Index: 7002234 (Open Web Text)

Max Activating Token Index: 475

Text #7

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.7150. Min Act: -0.1700

Data Index: 2741919 (Open Web Text)

Max Activating Token Index: 104

Text #8

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.6563. Min Act: -0.1700

Data Index: 8563203 (Open Web Text)

Max Activating Token Index: 601

Text #9

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.7000. Min Act: -0.1700

Data Index: 6040517 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.6673. Min Act: -0.1700

Data Index: 2312067 (Open Web Text)

Max Activating Token Index: 238

Text #11

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.7089. Min Act: -0.1700

Data Index: 5355951 (Open Web Text)

Max Activating Token Index: 390

Text #12

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.6731. Min Act: -0.1700

Data Index: 4474935 (Open Web Text)

Max Activating Token Index: 317

Text #13

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.7039. Min Act: -0.1700

Data Index: 7196608 (Open Web Text)

Max Activating Token Index: 615

Text #14

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.6326. Min Act: -0.1700

Data Index: 1363484 (Open Web Text)

Max Activating Token Index: 485

Text #15

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.6554. Min Act: -0.1700

Data Index: 7659387 (Open Web Text)

Max Activating Token Index: 807

Text #16

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.7126. Min Act: -0.1700

Data Index: 72573 (Open Web Text)

Max Activating Token Index: 688

Text #17

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.6505. Min Act: -0.1700

Data Index: 5311243 (Open Web Text)

Max Activating Token Index: 715

Text #18

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.6888. Min Act: -0.1700

Data Index: 3028046 (Open Web Text)

Max Activating Token Index: 32

Text #19

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.6934. Min Act: -0.1700

Data Index: 2372286 (Open Web Text)

Max Activating Token Index: 334