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

Dataset: Open Web Text

Neuron 1267 in Layer 2

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: 1.4472. Min Range: -1.4472

Max Act: 1.4472. Min Act: -0.1700

Data Index: 1503872 (Open Web Text)

Max Activating Token Index: 928

Text #1

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.4329. Min Act: -0.1700

Data Index: 7705607 (Open Web Text)

Max Activating Token Index: 234

Text #2

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.4273. Min Act: -0.1700

Data Index: 8409319 (Open Web Text)

Max Activating Token Index: 558

Text #3

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.4142. Min Act: -0.1700

Data Index: 741201 (Open Web Text)

Max Activating Token Index: 994

Text #4

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.4021. Min Act: -0.1700

Data Index: 3157403 (Open Web Text)

Max Activating Token Index: 882

Text #5

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.4032. Min Act: -0.1700

Data Index: 6440488 (Open Web Text)

Max Activating Token Index: 296

Text #6

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3695. Min Act: -0.1699

Data Index: 7076132 (Open Web Text)

Max Activating Token Index: 880

Text #7

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.4011. Min Act: -0.1700

Data Index: 5722078 (Open Web Text)

Max Activating Token Index: 496

Text #8

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3598. Min Act: -0.1700

Data Index: 912499 (Open Web Text)

Max Activating Token Index: 950

Text #9

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3671. Min Act: -0.1700

Data Index: 8270518 (Open Web Text)

Max Activating Token Index: 541

Text #10

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3727. Min Act: -0.1700

Data Index: 2912668 (Open Web Text)

Max Activating Token Index: 589

Text #11

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3613. Min Act: -0.1700

Data Index: 1234724 (Open Web Text)

Max Activating Token Index: 572

Text #12

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3720. Min Act: -0.1700

Data Index: 3856087 (Open Web Text)

Max Activating Token Index: 1002

Text #13

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3629. Min Act: -0.1700

Data Index: 5894378 (Open Web Text)

Max Activating Token Index: 627

Text #14

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3398. Min Act: -0.1700

Data Index: 4723516 (Open Web Text)

Max Activating Token Index: 923

Text #15

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3667. Min Act: -0.1700

Data Index: 8008122 (Open Web Text)

Max Activating Token Index: 835

Text #16

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3594. Min Act: -0.1698

Data Index: 1541099 (Open Web Text)

Max Activating Token Index: 885

Text #17

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3348. Min Act: -0.1698

Data Index: 7150869 (Open Web Text)

Max Activating Token Index: 561

Text #18

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3491. Min Act: -0.1700

Data Index: 5950406 (Open Web Text)

Max Activating Token Index: 242

Text #19

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3360. Min Act: -0.1700

Data Index: 5668286 (Open Web Text)

Max Activating Token Index: 409