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

Dataset: Open Web Text

Neuron 154 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: 3.3629. Min Range: -3.3629

Max Act: 3.3629. Min Act: -0.1700

Data Index: 1883280 (Open Web Text)

Max Activating Token Index: 104

Text #1

Max Range: 3.3629. Min Range: -3.3629

Max Act: 3.3046. Min Act: -0.1700

Data Index: 205746 (Open Web Text)

Max Activating Token Index: 275

Text #2

Max Range: 3.3629. Min Range: -3.3629

Max Act: 3.2622. Min Act: -0.1700

Data Index: 4584570 (Open Web Text)

Max Activating Token Index: 876

Text #3

Max Range: 3.3629. Min Range: -3.3629

Max Act: 3.2852. Min Act: -0.1700

Data Index: 6197473 (Open Web Text)

Max Activating Token Index: 275

Text #4

Max Range: 3.3629. Min Range: -3.3629

Max Act: 3.2536. Min Act: -0.1700

Data Index: 3581219 (Open Web Text)

Max Activating Token Index: 519

Text #5

Max Range: 3.3629. Min Range: -3.3629

Max Act: 3.2167. Min Act: -0.1700

Data Index: 3507126 (Open Web Text)

Max Activating Token Index: 899

Text #6

Max Range: 3.3629. Min Range: -3.3629

Max Act: 3.1936. Min Act: -0.1700

Data Index: 2083149 (Open Web Text)

Max Activating Token Index: 688

Text #7

Max Range: 3.3629. Min Range: -3.3629

Max Act: 3.1851. Min Act: -0.1700

Data Index: 3305967 (Open Web Text)

Max Activating Token Index: 864

Text #8

Max Range: 3.3629. Min Range: -3.3629

Max Act: 3.1506. Min Act: -0.1700

Data Index: 7648043 (Open Web Text)

Max Activating Token Index: 425

Text #9

Max Range: 3.3629. Min Range: -3.3629

Max Act: 3.1421. Min Act: -0.1700

Data Index: 1235548 (Open Web Text)

Max Activating Token Index: 581

Text #10

Max Range: 3.3629. Min Range: -3.3629

Max Act: 3.1423. Min Act: -0.1700

Data Index: 80271 (Open Web Text)

Max Activating Token Index: 401

Text #11

Max Range: 3.3629. Min Range: -3.3629

Max Act: 3.1439. Min Act: -0.1700

Data Index: 650860 (Open Web Text)

Max Activating Token Index: 669

Text #12

Max Range: 3.3629. Min Range: -3.3629

Max Act: 3.0951. Min Act: -0.1700

Data Index: 5788153 (Open Web Text)

Max Activating Token Index: 674

Text #13

Max Range: 3.3629. Min Range: -3.3629

Max Act: 3.1184. Min Act: -0.1700

Data Index: 4684070 (Open Web Text)

Max Activating Token Index: 277

Text #14

Max Range: 3.3629. Min Range: -3.3629

Max Act: 3.1329. Min Act: -0.1700

Data Index: 3593736 (Open Web Text)

Max Activating Token Index: 534

Text #15

Max Range: 3.3629. Min Range: -3.3629

Max Act: 3.1308. Min Act: -0.1700

Data Index: 8359768 (Open Web Text)

Max Activating Token Index: 637

Text #16

Max Range: 3.3629. Min Range: -3.3629

Max Act: 3.1204. Min Act: -0.1700

Data Index: 8472728 (Open Web Text)

Max Activating Token Index: 634

Text #17

Max Range: 3.3629. Min Range: -3.3629

Max Act: 3.1122. Min Act: -0.1700

Data Index: 3447119 (Open Web Text)

Max Activating Token Index: 550

Text #18

Max Range: 3.3629. Min Range: -3.3629

Max Act: 3.0891. Min Act: -0.1700

Data Index: 5265411 (Open Web Text)

Max Activating Token Index: 254

Text #19

Max Range: 3.3629. Min Range: -3.3629

Max Act: 3.0974. Min Act: -0.1700

Data Index: 5792574 (Open Web Text)

Max Activating Token Index: 149