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

Dataset: Open Web Text

Neuron 2953 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: 5.0402. Min Range: -5.0402

Max Act: 5.0402. Min Act: -0.1700

Data Index: 6012134 (Open Web Text)

Max Activating Token Index: 567

Text #1

Max Range: 5.0402. Min Range: -5.0402

Max Act: 5.0041. Min Act: -0.1700

Data Index: 7098787 (Open Web Text)

Max Activating Token Index: 758

Text #2

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.9509. Min Act: -0.1700

Data Index: 7149740 (Open Web Text)

Max Activating Token Index: 826

Text #3

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.9453. Min Act: -0.1700

Data Index: 819742 (Open Web Text)

Max Activating Token Index: 602

Text #4

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.9347. Min Act: -0.1700

Data Index: 7273765 (Open Web Text)

Max Activating Token Index: 963

Text #5

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.9436. Min Act: -0.1700

Data Index: 8454720 (Open Web Text)

Max Activating Token Index: 302

Text #6

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.9380. Min Act: -0.1700

Data Index: 7434620 (Open Web Text)

Max Activating Token Index: 583

Text #7

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.9044. Min Act: -0.1700

Data Index: 2000927 (Open Web Text)

Max Activating Token Index: 258

Text #8

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.8600. Min Act: -0.1700

Data Index: 942505 (Open Web Text)

Max Activating Token Index: 293

Text #9

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.8832. Min Act: -0.1700

Data Index: 6021678 (Open Web Text)

Max Activating Token Index: 548

Text #10

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.8836. Min Act: -0.1700

Data Index: 5518804 (Open Web Text)

Max Activating Token Index: 487

Text #11

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.8985. Min Act: -0.1700

Data Index: 2359311 (Open Web Text)

Max Activating Token Index: 968

Text #12

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.9086. Min Act: -0.1700

Data Index: 4087329 (Open Web Text)

Max Activating Token Index: 581

Text #13

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.8252. Min Act: -0.1700

Data Index: 7319405 (Open Web Text)

Max Activating Token Index: 439

Text #14

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.7943. Min Act: -0.1700

Data Index: 4174357 (Open Web Text)

Max Activating Token Index: 553

Text #15

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.8411. Min Act: -0.1700

Data Index: 763917 (Open Web Text)

Max Activating Token Index: 845

Text #16

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.8306. Min Act: -0.1700

Data Index: 3786856 (Open Web Text)

Max Activating Token Index: 815

Text #17

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.8421. Min Act: -0.1700

Data Index: 395312 (Open Web Text)

Max Activating Token Index: 665

Text #18

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.8290. Min Act: -0.1700

Data Index: 6997886 (Open Web Text)

Max Activating Token Index: 995

Text #19

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.8082. Min Act: -0.1700

Data Index: 979709 (Open Web Text)

Max Activating Token Index: 660