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

Dataset: Open Web Text

Neuron 2948 in Layer 1

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: 2.3676. Min Range: -2.3676

Max Act: 2.3421. Min Act: -0.1700

Data Index: 2449427 (Open Web Text)

Max Activating Token Index: 320

Text #1

Max Range: 2.3676. Min Range: -2.3676

Max Act: 2.3676. Min Act: -0.1700

Data Index: 3120147 (Open Web Text)

Max Activating Token Index: 378

Text #2

Max Range: 2.3676. Min Range: -2.3676

Max Act: 2.3638. Min Act: -0.1700

Data Index: 3650758 (Open Web Text)

Max Activating Token Index: 593

Text #3

Max Range: 2.3676. Min Range: -2.3676

Max Act: 2.3413. Min Act: -0.1700

Data Index: 4917312 (Open Web Text)

Max Activating Token Index: 382

Text #4

Max Range: 2.3676. Min Range: -2.3676

Max Act: 2.3274. Min Act: -0.1700

Data Index: 999304 (Open Web Text)

Max Activating Token Index: 399

Text #5

Max Range: 2.3676. Min Range: -2.3676

Max Act: 2.3292. Min Act: -0.1700

Data Index: 7631102 (Open Web Text)

Max Activating Token Index: 347

Text #6

Max Range: 2.3676. Min Range: -2.3676

Max Act: 2.3087. Min Act: -0.1700

Data Index: 6877872 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 2.3676. Min Range: -2.3676

Max Act: 2.2832. Min Act: -0.1700

Data Index: 4870511 (Open Web Text)

Max Activating Token Index: 554

Text #8

Max Range: 2.3676. Min Range: -2.3676

Max Act: 2.2838. Min Act: -0.1700

Data Index: 8591215 (Open Web Text)

Max Activating Token Index: 219

Text #9

Max Range: 2.3676. Min Range: -2.3676

Max Act: 2.2939. Min Act: -0.1700

Data Index: 4271193 (Open Web Text)

Max Activating Token Index: 556

Text #10

Max Range: 2.3676. Min Range: -2.3676

Max Act: 2.2694. Min Act: -0.1700

Data Index: 5821181 (Open Web Text)

Max Activating Token Index: 313

Text #11

Max Range: 2.3676. Min Range: -2.3676

Max Act: 2.2749. Min Act: -0.1700

Data Index: 5440973 (Open Web Text)

Max Activating Token Index: 231

Text #12

Max Range: 2.3676. Min Range: -2.3676

Max Act: 2.2707. Min Act: -0.1700

Data Index: 4189184 (Open Web Text)

Max Activating Token Index: 186

Text #13

Max Range: 2.3676. Min Range: -2.3676

Max Act: 2.2687. Min Act: -0.1700

Data Index: 2635325 (Open Web Text)

Max Activating Token Index: 274

Text #14

Max Range: 2.3676. Min Range: -2.3676

Max Act: 2.2649. Min Act: -0.1700

Data Index: 4822980 (Open Web Text)

Max Activating Token Index: 517

Text #15

Max Range: 2.3676. Min Range: -2.3676

Max Act: 2.2683. Min Act: -0.1700

Data Index: 3108652 (Open Web Text)

Max Activating Token Index: 244

Text #16

Max Range: 2.3676. Min Range: -2.3676

Max Act: 2.2618. Min Act: -0.1700

Data Index: 3882004 (Open Web Text)

Max Activating Token Index: 554

Text #17

Max Range: 2.3676. Min Range: -2.3676

Max Act: 2.2657. Min Act: -0.1700

Data Index: 4746844 (Open Web Text)

Max Activating Token Index: 225

Text #18

Max Range: 2.3676. Min Range: -2.3676

Max Act: 2.2479. Min Act: -0.1700

Data Index: 8105548 (Open Web Text)

Max Activating Token Index: 540

Text #19

Max Range: 2.3676. Min Range: -2.3676

Max Act: 2.2462. Min Act: -0.1700

Data Index: 1797882 (Open Web Text)

Max Activating Token Index: 347