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

Dataset: Open Web Text

Neuron 2577 in Layer 3

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: 4.7316. Min Range: -4.7316

Max Act: 4.7316. Min Act: -0.1700

Data Index: 1731292 (Open Web Text)

Max Activating Token Index: 569

Text #1

Max Range: 4.7316. Min Range: -4.7316

Max Act: 4.6915. Min Act: -0.1700

Data Index: 5846486 (Open Web Text)

Max Activating Token Index: 181

Text #2

Max Range: 4.7316. Min Range: -4.7316

Max Act: 4.6836. Min Act: -0.1700

Data Index: 3259995 (Open Web Text)

Max Activating Token Index: 147

Text #3

Max Range: 4.7316. Min Range: -4.7316

Max Act: 4.6768. Min Act: -0.1700

Data Index: 2545588 (Open Web Text)

Max Activating Token Index: 464

Text #4

Max Range: 4.7316. Min Range: -4.7316

Max Act: 4.7020. Min Act: -0.1700

Data Index: 1116969 (Open Web Text)

Max Activating Token Index: 104

Text #5

Max Range: 4.7316. Min Range: -4.7316

Max Act: 4.7051. Min Act: -0.1700

Data Index: 736357 (Open Web Text)

Max Activating Token Index: 574

Text #6

Max Range: 4.7316. Min Range: -4.7316

Max Act: 4.6948. Min Act: -0.1700

Data Index: 586998 (Open Web Text)

Max Activating Token Index: 402

Text #7

Max Range: 4.7316. Min Range: -4.7316

Max Act: 4.6636. Min Act: -0.1700

Data Index: 904560 (Open Web Text)

Max Activating Token Index: 511

Text #8

Max Range: 4.7316. Min Range: -4.7316

Max Act: 4.6681. Min Act: -0.1700

Data Index: 391349 (Open Web Text)

Max Activating Token Index: 564

Text #9

Max Range: 4.7316. Min Range: -4.7316

Max Act: 4.6775. Min Act: -0.1700

Data Index: 6175042 (Open Web Text)

Max Activating Token Index: 485

Text #10

Max Range: 4.7316. Min Range: -4.7316

Max Act: 4.6721. Min Act: -0.1700

Data Index: 6921785 (Open Web Text)

Max Activating Token Index: 599

Text #11

Max Range: 4.7316. Min Range: -4.7316

Max Act: 4.6705. Min Act: -0.1700

Data Index: 5879355 (Open Web Text)

Max Activating Token Index: 429

Text #12

Max Range: 4.7316. Min Range: -4.7316

Max Act: 4.6615. Min Act: -0.1700

Data Index: 7429085 (Open Web Text)

Max Activating Token Index: 462

Text #13

Max Range: 4.7316. Min Range: -4.7316

Max Act: 4.7005. Min Act: -0.1700

Data Index: 7552259 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 4.7316. Min Range: -4.7316

Max Act: 4.6582. Min Act: -0.1700

Data Index: 3851593 (Open Web Text)

Max Activating Token Index: 937

Text #15

Max Range: 4.7316. Min Range: -4.7316

Max Act: 4.6815. Min Act: -0.1700

Data Index: 862119 (Open Web Text)

Max Activating Token Index: 570

Text #16

Max Range: 4.7316. Min Range: -4.7316

Max Act: 4.6351. Min Act: -0.1700

Data Index: 3999039 (Open Web Text)

Max Activating Token Index: 312

Text #17

Max Range: 4.7316. Min Range: -4.7316

Max Act: 4.6561. Min Act: -0.1700

Data Index: 1112948 (Open Web Text)

Max Activating Token Index: 433

Text #18

Max Range: 4.7316. Min Range: -4.7316

Max Act: 4.6408. Min Act: -0.1700

Data Index: 4767945 (Open Web Text)

Max Activating Token Index: 208

Text #19

Max Range: 4.7316. Min Range: -4.7316

Max Act: 4.6638. Min Act: -0.1700

Data Index: 4801363 (Open Web Text)

Max Activating Token Index: 528