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

Dataset: Open Web Text

Neuron 1089 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: 1.8903. Min Range: -1.8903

Max Act: 1.8903. Min Act: -0.1700

Data Index: 8477877 (Open Web Text)

Max Activating Token Index: 162

Text #1

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.8351. Min Act: -0.1700

Data Index: 8730154 (Open Web Text)

Max Activating Token Index: 44

Text #2

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.8395. Min Act: -0.1700

Data Index: 4121753 (Open Web Text)

Max Activating Token Index: 927

Text #3

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.8355. Min Act: -0.1700

Data Index: 1302541 (Open Web Text)

Max Activating Token Index: 513

Text #4

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.8545. Min Act: -0.1700

Data Index: 1904343 (Open Web Text)

Max Activating Token Index: 346

Text #5

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.8571. Min Act: -0.1700

Data Index: 3970897 (Open Web Text)

Max Activating Token Index: 66

Text #6

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.8561. Min Act: -0.1700

Data Index: 8081076 (Open Web Text)

Max Activating Token Index: 487

Text #7

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.8300. Min Act: -0.1700

Data Index: 6772460 (Open Web Text)

Max Activating Token Index: 182

Text #8

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.8370. Min Act: -0.1700

Data Index: 1655750 (Open Web Text)

Max Activating Token Index: 336

Text #9

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.8254. Min Act: -0.1700

Data Index: 60761 (Open Web Text)

Max Activating Token Index: 442

Text #10

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.8329. Min Act: -0.1700

Data Index: 7716383 (Open Web Text)

Max Activating Token Index: 168

Text #11

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.8181. Min Act: -0.1700

Data Index: 1343792 (Open Web Text)

Max Activating Token Index: 942

Text #12

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.8168. Min Act: -0.1700

Data Index: 2102601 (Open Web Text)

Max Activating Token Index: 354

Text #13

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.8031. Min Act: -0.1700

Data Index: 389436 (Open Web Text)

Max Activating Token Index: 149

Text #14

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.8118. Min Act: -0.1700

Data Index: 1763023 (Open Web Text)

Max Activating Token Index: 55

Text #15

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.8054. Min Act: -0.1700

Data Index: 4540425 (Open Web Text)

Max Activating Token Index: 306

Text #16

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.7958. Min Act: -0.1700

Data Index: 3251053 (Open Web Text)

Max Activating Token Index: 78

Text #17

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.8077. Min Act: -0.1700

Data Index: 690710 (Open Web Text)

Max Activating Token Index: 812

Text #18

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.7964. Min Act: -0.1700

Data Index: 7603799 (Open Web Text)

Max Activating Token Index: 533

Text #19

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.7999. Min Act: -0.1700

Data Index: 6437461 (Open Web Text)

Max Activating Token Index: 232