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

Dataset: Open Web Text

Neuron 2817 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: 4.0349. Min Range: -4.0349

Max Act: 4.0349. Min Act: -0.1700

Data Index: 5912066 (Open Web Text)

Max Activating Token Index: 580

Text #1

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.9214. Min Act: -0.1700

Data Index: 2354671 (Open Web Text)

Max Activating Token Index: 618

Text #2

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.9043. Min Act: -0.1700

Data Index: 4638674 (Open Web Text)

Max Activating Token Index: 45

Text #3

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.8878. Min Act: -0.1700

Data Index: 5249498 (Open Web Text)

Max Activating Token Index: 765

Text #4

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.8798. Min Act: -0.1700

Data Index: 5357560 (Open Web Text)

Max Activating Token Index: 269

Text #5

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.8905. Min Act: -0.1700

Data Index: 3633797 (Open Web Text)

Max Activating Token Index: 440

Text #6

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.8673. Min Act: -0.1700

Data Index: 4282359 (Open Web Text)

Max Activating Token Index: 662

Text #7

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.8665. Min Act: -0.1700

Data Index: 8003440 (Open Web Text)

Max Activating Token Index: 677

Text #8

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.8604. Min Act: -0.1700

Data Index: 1893958 (Open Web Text)

Max Activating Token Index: 515

Text #9

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.8654. Min Act: -0.1700

Data Index: 155894 (Open Web Text)

Max Activating Token Index: 660

Text #10

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.8721. Min Act: -0.1700

Data Index: 2705832 (Open Web Text)

Max Activating Token Index: 198

Text #11

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.8469. Min Act: -0.1700

Data Index: 3227107 (Open Web Text)

Max Activating Token Index: 431

Text #12

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.8291. Min Act: -0.1700

Data Index: 6186268 (Open Web Text)

Max Activating Token Index: 375

Text #13

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.8351. Min Act: -0.1700

Data Index: 1139522 (Open Web Text)

Max Activating Token Index: 592

Text #14

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.8188. Min Act: -0.1700

Data Index: 3464541 (Open Web Text)

Max Activating Token Index: 289

Text #15

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.8200. Min Act: -0.1700

Data Index: 6356184 (Open Web Text)

Max Activating Token Index: 169

Text #16

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.8479. Min Act: -0.1700

Data Index: 7481900 (Open Web Text)

Max Activating Token Index: 636

Text #17

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.8300. Min Act: -0.1700

Data Index: 5228553 (Open Web Text)

Max Activating Token Index: 588

Text #18

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.8452. Min Act: -0.1700

Data Index: 4174501 (Open Web Text)

Max Activating Token Index: 787

Text #19

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.8261. Min Act: -0.1700

Data Index: 8744802 (Open Web Text)

Max Activating Token Index: 520