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

Dataset: Open Web Text

Neuron 3032 in Layer 6

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: 4.1333. Min Range: -4.1333

Max Act: 4.1333. Min Act: -0.1700

Data Index: 8615917 (Open Web Text)

Max Activating Token Index: 534

Text #1

Max Range: 4.1333. Min Range: -4.1333

Max Act: 4.0794. Min Act: -0.1700

Data Index: 20415 (Open Web Text)

Max Activating Token Index: 967

Text #2

Max Range: 4.1333. Min Range: -4.1333

Max Act: 4.0279. Min Act: -0.1700

Data Index: 4230456 (Open Web Text)

Max Activating Token Index: 273

Text #3

Max Range: 4.1333. Min Range: -4.1333

Max Act: 4.0061. Min Act: -0.1700

Data Index: 6597425 (Open Web Text)

Max Activating Token Index: 733

Text #4

Max Range: 4.1333. Min Range: -4.1333

Max Act: 3.9978. Min Act: -0.1700

Data Index: 4013472 (Open Web Text)

Max Activating Token Index: 1013

Text #5

Max Range: 4.1333. Min Range: -4.1333

Max Act: 4.0202. Min Act: -0.1700

Data Index: 3418924 (Open Web Text)

Max Activating Token Index: 841

Text #6

Max Range: 4.1333. Min Range: -4.1333

Max Act: 3.9822. Min Act: -0.1700

Data Index: 4831307 (Open Web Text)

Max Activating Token Index: 919

Text #7

Max Range: 4.1333. Min Range: -4.1333

Max Act: 3.9438. Min Act: -0.1700

Data Index: 8351816 (Open Web Text)

Max Activating Token Index: 741

Text #8

Max Range: 4.1333. Min Range: -4.1333

Max Act: 4.0039. Min Act: -0.1700

Data Index: 6997758 (Open Web Text)

Max Activating Token Index: 48

Text #9

Max Range: 4.1333. Min Range: -4.1333

Max Act: 3.9895. Min Act: -0.1700

Data Index: 6410456 (Open Web Text)

Max Activating Token Index: 679

Text #10

Max Range: 4.1333. Min Range: -4.1333

Max Act: 3.9882. Min Act: -0.1700

Data Index: 7187147 (Open Web Text)

Max Activating Token Index: 430

Text #11

Max Range: 4.1333. Min Range: -4.1333

Max Act: 3.9236. Min Act: -0.1700

Data Index: 4928141 (Open Web Text)

Max Activating Token Index: 870

Text #12

Max Range: 4.1333. Min Range: -4.1333

Max Act: 3.9026. Min Act: -0.1700

Data Index: 5312764 (Open Web Text)

Max Activating Token Index: 591

Text #13

Max Range: 4.1333. Min Range: -4.1333

Max Act: 3.8577. Min Act: -0.1700

Data Index: 746420 (Open Web Text)

Max Activating Token Index: 891

Text #14

Max Range: 4.1333. Min Range: -4.1333

Max Act: 3.8399. Min Act: -0.1700

Data Index: 2455549 (Open Web Text)

Max Activating Token Index: 226

Text #15

Max Range: 4.1333. Min Range: -4.1333

Max Act: 3.8380. Min Act: -0.1700

Data Index: 6680528 (Open Web Text)

Max Activating Token Index: 671

Text #16

Max Range: 4.1333. Min Range: -4.1333

Max Act: 3.8485. Min Act: -0.1700

Data Index: 5341384 (Open Web Text)

Max Activating Token Index: 191

Text #17

Max Range: 4.1333. Min Range: -4.1333

Max Act: 3.8055. Min Act: -0.1700

Data Index: 7878110 (Open Web Text)

Max Activating Token Index: 756

Text #18

Max Range: 4.1333. Min Range: -4.1333

Max Act: 3.8331. Min Act: -0.1700

Data Index: 6416360 (Open Web Text)

Max Activating Token Index: 921

Text #19

Max Range: 4.1333. Min Range: -4.1333

Max Act: 3.8004. Min Act: -0.1700

Data Index: 6546232 (Open Web Text)

Max Activating Token Index: 713