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

Dataset: Open Web Text

Neuron 1459 in Layer 0

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: 3.6451. Min Range: -3.6451

Max Act: 3.6451. Min Act: -0.1700

Data Index: 7068540 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.5568. Min Act: -0.1700

Data Index: 5581681 (Open Web Text)

Max Activating Token Index: 711

Text #2

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.5908. Min Act: -0.1700

Data Index: 772300 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.5339. Min Act: -0.1700

Data Index: 3353176 (Open Web Text)

Max Activating Token Index: 827

Text #4

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.5171. Min Act: -0.1700

Data Index: 1299159 (Open Web Text)

Max Activating Token Index: 576

Text #5

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.5009. Min Act: -0.1700

Data Index: 1142142 (Open Web Text)

Max Activating Token Index: 690

Text #6

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.4440. Min Act: -0.1700

Data Index: 4928110 (Open Web Text)

Max Activating Token Index: 1002

Text #7

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.4411. Min Act: -0.1700

Data Index: 890149 (Open Web Text)

Max Activating Token Index: 12

Text #8

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.4345. Min Act: -0.1700

Data Index: 5577075 (Open Web Text)

Max Activating Token Index: 687

Text #9

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.4342. Min Act: -0.1700

Data Index: 833449 (Open Web Text)

Max Activating Token Index: 651

Text #10

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.4498. Min Act: -0.1700

Data Index: 2158594 (Open Web Text)

Max Activating Token Index: 1022

Text #11

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.4670. Min Act: -0.1700

Data Index: 2017225 (Open Web Text)

Max Activating Token Index: 952

Text #12

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.4350. Min Act: -0.1700

Data Index: 5359452 (Open Web Text)

Max Activating Token Index: 12

Text #13

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.4433. Min Act: -0.1700

Data Index: 3070629 (Open Web Text)

Max Activating Token Index: 704

Text #14

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.4428. Min Act: -0.1700

Data Index: 4127556 (Open Web Text)

Max Activating Token Index: 708

Text #15

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.4400. Min Act: -0.1700

Data Index: 2729261 (Open Web Text)

Max Activating Token Index: 992

Text #16

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.4224. Min Act: -0.1700

Data Index: 4123346 (Open Web Text)

Max Activating Token Index: 721

Text #17

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.4550. Min Act: -0.1700

Data Index: 3828612 (Open Web Text)

Max Activating Token Index: 721

Text #18

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.4443. Min Act: -0.1700

Data Index: 3637473 (Open Web Text)

Max Activating Token Index: 1020

Text #19

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.4540. Min Act: -0.1700

Data Index: 663305 (Open Web Text)

Max Activating Token Index: 778