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

Dataset: Open Web Text

Neuron 2122 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: 3.1242. Min Range: -3.1242

Max Act: 3.1242. Min Act: -0.1700

Data Index: 938141 (Open Web Text)

Max Activating Token Index: 155

Text #1

Max Range: 3.1242. Min Range: -3.1242

Max Act: 3.0828. Min Act: -0.1700

Data Index: 1845829 (Open Web Text)

Max Activating Token Index: 144

Text #2

Max Range: 3.1242. Min Range: -3.1242

Max Act: 3.0965. Min Act: -0.1700

Data Index: 2404551 (Open Web Text)

Max Activating Token Index: 778

Text #3

Max Range: 3.1242. Min Range: -3.1242

Max Act: 3.0915. Min Act: -0.1700

Data Index: 733571 (Open Web Text)

Max Activating Token Index: 516

Text #4

Max Range: 3.1242. Min Range: -3.1242

Max Act: 3.0781. Min Act: -0.1700

Data Index: 5849673 (Open Web Text)

Max Activating Token Index: 230

Text #5

Max Range: 3.1242. Min Range: -3.1242

Max Act: 3.0820. Min Act: -0.1700

Data Index: 1724826 (Open Web Text)

Max Activating Token Index: 353

Text #6

Max Range: 3.1242. Min Range: -3.1242

Max Act: 3.0677. Min Act: -0.1700

Data Index: 8128889 (Open Web Text)

Max Activating Token Index: 356

Text #7

Max Range: 3.1242. Min Range: -3.1242

Max Act: 3.0650. Min Act: -0.1700

Data Index: 6288433 (Open Web Text)

Max Activating Token Index: 201

Text #8

Max Range: 3.1242. Min Range: -3.1242

Max Act: 3.0555. Min Act: -0.1700

Data Index: 7473206 (Open Web Text)

Max Activating Token Index: 717

Text #9

Max Range: 3.1242. Min Range: -3.1242

Max Act: 3.0603. Min Act: -0.1700

Data Index: 1198356 (Open Web Text)

Max Activating Token Index: 82

Text #10

Max Range: 3.1242. Min Range: -3.1242

Max Act: 3.0578. Min Act: -0.1700

Data Index: 7741144 (Open Web Text)

Max Activating Token Index: 134

Text #11

Max Range: 3.1242. Min Range: -3.1242

Max Act: 3.0403. Min Act: -0.1700

Data Index: 1603381 (Open Web Text)

Max Activating Token Index: 554

Text #12

Max Range: 3.1242. Min Range: -3.1242

Max Act: 3.0445. Min Act: -0.1700

Data Index: 5611807 (Open Web Text)

Max Activating Token Index: 483

Text #13

Max Range: 3.1242. Min Range: -3.1242

Max Act: 3.0390. Min Act: -0.1700

Data Index: 1883458 (Open Web Text)

Max Activating Token Index: 181

Text #14

Max Range: 3.1242. Min Range: -3.1242

Max Act: 3.0377. Min Act: -0.1700

Data Index: 2612642 (Open Web Text)

Max Activating Token Index: 396

Text #15

Max Range: 3.1242. Min Range: -3.1242

Max Act: 3.0317. Min Act: -0.1700

Data Index: 6357137 (Open Web Text)

Max Activating Token Index: 592

Text #16

Max Range: 3.1242. Min Range: -3.1242

Max Act: 3.0274. Min Act: -0.1700

Data Index: 6389099 (Open Web Text)

Max Activating Token Index: 687

Text #17

Max Range: 3.1242. Min Range: -3.1242

Max Act: 3.0318. Min Act: -0.1700

Data Index: 1626130 (Open Web Text)

Max Activating Token Index: 110

Text #18

Max Range: 3.1242. Min Range: -3.1242

Max Act: 3.0022. Min Act: -0.1700

Data Index: 3222460 (Open Web Text)

Max Activating Token Index: 566

Text #19

Max Range: 3.1242. Min Range: -3.1242

Max Act: 3.0269. Min Act: -0.1700

Data Index: 5545954 (Open Web Text)

Max Activating Token Index: 695