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

Dataset: Open Web Text

Neuron 2978 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: 3.6839. Min Range: -3.6839

Max Act: 3.6839. Min Act: -0.1700

Data Index: 6874024 (Open Web Text)

Max Activating Token Index: 823

Text #1

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.4252. Min Act: -0.1700

Data Index: 1318270 (Open Web Text)

Max Activating Token Index: 908

Text #2

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.4207. Min Act: -0.1700

Data Index: 1686635 (Open Web Text)

Max Activating Token Index: 141

Text #3

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.3625. Min Act: -0.1700

Data Index: 2966315 (Open Web Text)

Max Activating Token Index: 997

Text #4

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.3378. Min Act: -0.1700

Data Index: 3882782 (Open Web Text)

Max Activating Token Index: 986

Text #5

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.3295. Min Act: -0.1700

Data Index: 7466296 (Open Web Text)

Max Activating Token Index: 862

Text #6

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.3344. Min Act: -0.1700

Data Index: 967304 (Open Web Text)

Max Activating Token Index: 922

Text #7

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.3040. Min Act: -0.1700

Data Index: 6375653 (Open Web Text)

Max Activating Token Index: 338

Text #8

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.2956. Min Act: -0.1700

Data Index: 8068276 (Open Web Text)

Max Activating Token Index: 102

Text #9

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.2723. Min Act: -0.1700

Data Index: 8333362 (Open Web Text)

Max Activating Token Index: 789

Text #10

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.3173. Min Act: -0.1700

Data Index: 8759742 (Open Web Text)

Max Activating Token Index: 454

Text #11

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.2488. Min Act: -0.1700

Data Index: 2825386 (Open Web Text)

Max Activating Token Index: 565

Text #12

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.2449. Min Act: -0.1700

Data Index: 1401937 (Open Web Text)

Max Activating Token Index: 564

Text #13

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.2460. Min Act: -0.1700

Data Index: 7679042 (Open Web Text)

Max Activating Token Index: 228

Text #14

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.2321. Min Act: -0.1700

Data Index: 1923840 (Open Web Text)

Max Activating Token Index: 1002

Text #15

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.2542. Min Act: -0.1700

Data Index: 6238099 (Open Web Text)

Max Activating Token Index: 363

Text #16

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.2704. Min Act: -0.1700

Data Index: 452289 (Open Web Text)

Max Activating Token Index: 75

Text #17

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.2644. Min Act: -0.1700

Data Index: 2869819 (Open Web Text)

Max Activating Token Index: 391

Text #18

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.2591. Min Act: -0.1700

Data Index: 3487911 (Open Web Text)

Max Activating Token Index: 511

Text #19

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.2382. Min Act: -0.1700

Data Index: 8740387 (Open Web Text)

Max Activating Token Index: 643