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

Dataset: Open Web Text

Neuron 1712 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: 1.8806. Min Range: -1.8806

Max Act: 1.8806. Min Act: -0.1700

Data Index: 5827214 (Open Web Text)

Max Activating Token Index: 484

Text #1

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.8420. Min Act: -0.1700

Data Index: 3465824 (Open Web Text)

Max Activating Token Index: 248

Text #2

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.8106. Min Act: -0.1700

Data Index: 787233 (Open Web Text)

Max Activating Token Index: 611

Text #3

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.8016. Min Act: -0.1700

Data Index: 5156172 (Open Web Text)

Max Activating Token Index: 92

Text #4

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.7969. Min Act: -0.1700

Data Index: 6321113 (Open Web Text)

Max Activating Token Index: 847

Text #5

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.7776. Min Act: -0.1700

Data Index: 3371850 (Open Web Text)

Max Activating Token Index: 587

Text #6

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.7814. Min Act: -0.1700

Data Index: 8829264 (Open Web Text)

Max Activating Token Index: 124

Text #7

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.7661. Min Act: -0.1700

Data Index: 2703600 (Open Web Text)

Max Activating Token Index: 540

Text #8

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.7570. Min Act: -0.1700

Data Index: 4859726 (Open Web Text)

Max Activating Token Index: 501

Text #9

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.7693. Min Act: -0.1700

Data Index: 3796345 (Open Web Text)

Max Activating Token Index: 276

Text #10

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.7643. Min Act: -0.1700

Data Index: 2513099 (Open Web Text)

Max Activating Token Index: 74

Text #11

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.7644. Min Act: -0.1700

Data Index: 6940805 (Open Web Text)

Max Activating Token Index: 739

Text #12

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.7715. Min Act: -0.1700

Data Index: 6665598 (Open Web Text)

Max Activating Token Index: 412

Text #13

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.7627. Min Act: -0.1700

Data Index: 5359355 (Open Web Text)

Max Activating Token Index: 442

Text #14

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.7657. Min Act: -0.1700

Data Index: 2062395 (Open Web Text)

Max Activating Token Index: 661

Text #15

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.7644. Min Act: -0.1700

Data Index: 1747909 (Open Web Text)

Max Activating Token Index: 620

Text #16

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.7498. Min Act: -0.1700

Data Index: 3945401 (Open Web Text)

Max Activating Token Index: 61

Text #17

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.7621. Min Act: -0.1700

Data Index: 1911771 (Open Web Text)

Max Activating Token Index: 181

Text #18

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.7547. Min Act: -0.1700

Data Index: 4834450 (Open Web Text)

Max Activating Token Index: 494

Text #19

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.7561. Min Act: -0.1700

Data Index: 2674660 (Open Web Text)

Max Activating Token Index: 467