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

Dataset: Open Web Text

Neuron 739 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: 3.3373. Min Range: -3.3373

Max Act: 3.3373. Min Act: -0.1700

Data Index: 7553322 (Open Web Text)

Max Activating Token Index: 451

Text #1

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.2771. Min Act: -0.1700

Data Index: 8779493 (Open Web Text)

Max Activating Token Index: 377

Text #2

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.1048. Min Act: -0.1700

Data Index: 4130215 (Open Web Text)

Max Activating Token Index: 228

Text #3

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.0934. Min Act: -0.1700

Data Index: 2062786 (Open Web Text)

Max Activating Token Index: 776

Text #4

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.0724. Min Act: -0.1700

Data Index: 7355616 (Open Web Text)

Max Activating Token Index: 540

Text #5

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.0476. Min Act: -0.1700

Data Index: 1064039 (Open Web Text)

Max Activating Token Index: 592

Text #6

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.0639. Min Act: -0.1700

Data Index: 2878561 (Open Web Text)

Max Activating Token Index: 610

Text #7

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.0619. Min Act: -0.1700

Data Index: 8314252 (Open Web Text)

Max Activating Token Index: 542

Text #8

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.0452. Min Act: -0.1700

Data Index: 6746685 (Open Web Text)

Max Activating Token Index: 837

Text #9

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.0497. Min Act: -0.1700

Data Index: 6588629 (Open Web Text)

Max Activating Token Index: 292

Text #10

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.0473. Min Act: -0.1700

Data Index: 913702 (Open Web Text)

Max Activating Token Index: 532

Text #11

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.0560. Min Act: -0.1700

Data Index: 6372591 (Open Web Text)

Max Activating Token Index: 687

Text #12

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.0303. Min Act: -0.1700

Data Index: 1732900 (Open Web Text)

Max Activating Token Index: 108

Text #13

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.0371. Min Act: -0.1700

Data Index: 7663897 (Open Web Text)

Max Activating Token Index: 522

Text #14

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.0357. Min Act: -0.1700

Data Index: 3352292 (Open Web Text)

Max Activating Token Index: 789

Text #15

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.0213. Min Act: -0.1700

Data Index: 8074881 (Open Web Text)

Max Activating Token Index: 998

Text #16

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.0427. Min Act: -0.1700

Data Index: 5048678 (Open Web Text)

Max Activating Token Index: 844

Text #17

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.0462. Min Act: -0.1700

Data Index: 807798 (Open Web Text)

Max Activating Token Index: 933

Text #18

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.0223. Min Act: -0.1700

Data Index: 6311197 (Open Web Text)

Max Activating Token Index: 741

Text #19

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.0259. Min Act: -0.1700

Data Index: 2327332 (Open Web Text)

Max Activating Token Index: 202