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

Dataset: Open Web Text

Neuron 46 in Layer 2

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: 3.0314. Min Range: -3.0314

Max Act: 3.0314. Min Act: -0.1700

Data Index: 3231531 (Open Web Text)

Max Activating Token Index: 104

Text #1

Max Range: 3.0314. Min Range: -3.0314

Max Act: 2.9397. Min Act: -0.1700

Data Index: 7591425 (Open Web Text)

Max Activating Token Index: 91

Text #2

Max Range: 3.0314. Min Range: -3.0314

Max Act: 2.9239. Min Act: -0.1700

Data Index: 5490967 (Open Web Text)

Max Activating Token Index: 871

Text #3

Max Range: 3.0314. Min Range: -3.0314

Max Act: 2.8809. Min Act: -0.1700

Data Index: 1795881 (Open Web Text)

Max Activating Token Index: 596

Text #4

Max Range: 3.0314. Min Range: -3.0314

Max Act: 2.8603. Min Act: -0.1700

Data Index: 3861608 (Open Web Text)

Max Activating Token Index: 122

Text #5

Max Range: 3.0314. Min Range: -3.0314

Max Act: 2.8679. Min Act: -0.1700

Data Index: 4099565 (Open Web Text)

Max Activating Token Index: 947

Text #6

Max Range: 3.0314. Min Range: -3.0314

Max Act: 2.8754. Min Act: -0.1700

Data Index: 3734955 (Open Web Text)

Max Activating Token Index: 484

Text #7

Max Range: 3.0314. Min Range: -3.0314

Max Act: 2.8532. Min Act: -0.1700

Data Index: 2350511 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 3.0314. Min Range: -3.0314

Max Act: 2.8417. Min Act: -0.1700

Data Index: 1418112 (Open Web Text)

Max Activating Token Index: 723

Text #9

Max Range: 3.0314. Min Range: -3.0314

Max Act: 2.8736. Min Act: -0.1700

Data Index: 5163376 (Open Web Text)

Max Activating Token Index: 455

Text #10

Max Range: 3.0314. Min Range: -3.0314

Max Act: 2.8618. Min Act: -0.1700

Data Index: 8192778 (Open Web Text)

Max Activating Token Index: 962

Text #11

Max Range: 3.0314. Min Range: -3.0314

Max Act: 2.8225. Min Act: -0.1700

Data Index: 1724005 (Open Web Text)

Max Activating Token Index: 492

Text #12

Max Range: 3.0314. Min Range: -3.0314

Max Act: 2.8363. Min Act: -0.1700

Data Index: 5886705 (Open Web Text)

Max Activating Token Index: 537

Text #13

Max Range: 3.0314. Min Range: -3.0314

Max Act: 2.8265. Min Act: -0.1700

Data Index: 2485864 (Open Web Text)

Max Activating Token Index: 837

Text #14

Max Range: 3.0314. Min Range: -3.0314

Max Act: 2.8017. Min Act: -0.1700

Data Index: 8064438 (Open Web Text)

Max Activating Token Index: 720

Text #15

Max Range: 3.0314. Min Range: -3.0314

Max Act: 2.7986. Min Act: -0.1700

Data Index: 7327421 (Open Web Text)

Max Activating Token Index: 522

Text #16

Max Range: 3.0314. Min Range: -3.0314

Max Act: 2.8184. Min Act: -0.1700

Data Index: 3432927 (Open Web Text)

Max Activating Token Index: 787

Text #17

Max Range: 3.0314. Min Range: -3.0314

Max Act: 2.7630. Min Act: -0.1700

Data Index: 3967029 (Open Web Text)

Max Activating Token Index: 519

Text #18

Max Range: 3.0314. Min Range: -3.0314

Max Act: 2.7923. Min Act: -0.1700

Data Index: 4641788 (Open Web Text)

Max Activating Token Index: 521

Text #19

Max Range: 3.0314. Min Range: -3.0314

Max Act: 2.7564. Min Act: -0.1700

Data Index: 6868606 (Open Web Text)

Max Activating Token Index: 738