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

Dataset: Open Web Text

Neuron 2116 in Layer 5

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: 3.4507. Min Range: -3.4507

Max Act: 3.4507. Min Act: -0.1700

Data Index: 4585639 (Open Web Text)

Max Activating Token Index: 724

Text #1

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.4378. Min Act: -0.1700

Data Index: 1217419 (Open Web Text)

Max Activating Token Index: 960

Text #2

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.3729. Min Act: -0.1700

Data Index: 2893794 (Open Web Text)

Max Activating Token Index: 360

Text #3

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.3645. Min Act: -0.1700

Data Index: 4098095 (Open Web Text)

Max Activating Token Index: 642

Text #4

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.3212. Min Act: -0.1700

Data Index: 2233534 (Open Web Text)

Max Activating Token Index: 62

Text #5

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.3129. Min Act: -0.1700

Data Index: 7840294 (Open Web Text)

Max Activating Token Index: 850

Text #6

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.3000. Min Act: -0.1700

Data Index: 7995574 (Open Web Text)

Max Activating Token Index: 305

Text #7

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.3032. Min Act: -0.1700

Data Index: 8048394 (Open Web Text)

Max Activating Token Index: 840

Text #8

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.2744. Min Act: -0.1700

Data Index: 3609345 (Open Web Text)

Max Activating Token Index: 436

Text #9

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.2837. Min Act: -0.1700

Data Index: 587037 (Open Web Text)

Max Activating Token Index: 543

Text #10

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.2845. Min Act: -0.1700

Data Index: 1722695 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.2751. Min Act: -0.1700

Data Index: 4595887 (Open Web Text)

Max Activating Token Index: 374

Text #12

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.2686. Min Act: -0.1700

Data Index: 7903230 (Open Web Text)

Max Activating Token Index: 196

Text #13

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.2450. Min Act: -0.1700

Data Index: 4382573 (Open Web Text)

Max Activating Token Index: 923

Text #14

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.2529. Min Act: -0.1700

Data Index: 7490759 (Open Web Text)

Max Activating Token Index: 87

Text #15

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.2513. Min Act: -0.1700

Data Index: 963461 (Open Web Text)

Max Activating Token Index: 296

Text #16

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.2294. Min Act: -0.1700

Data Index: 7374865 (Open Web Text)

Max Activating Token Index: 606

Text #17

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.2340. Min Act: -0.1700

Data Index: 7148473 (Open Web Text)

Max Activating Token Index: 137

Text #18

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.2368. Min Act: -0.1700

Data Index: 5369367 (Open Web Text)

Max Activating Token Index: 686

Text #19

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.2393. Min Act: -0.1700

Data Index: 1734562 (Open Web Text)

Max Activating Token Index: 394