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

Dataset: Open Web Text

Neuron 356 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: 3.7523. Min Range: -3.7523

Max Act: 3.7523. Min Act: -0.1700

Data Index: 2131919 (Open Web Text)

Max Activating Token Index: 473

Text #1

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.7428. Min Act: -0.1700

Data Index: 6278256 (Open Web Text)

Max Activating Token Index: 578

Text #2

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.7149. Min Act: -0.1700

Data Index: 3437239 (Open Web Text)

Max Activating Token Index: 471

Text #3

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.7099. Min Act: -0.1700

Data Index: 7965945 (Open Web Text)

Max Activating Token Index: 442

Text #4

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.7004. Min Act: -0.1700

Data Index: 8437893 (Open Web Text)

Max Activating Token Index: 999

Text #5

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.6752. Min Act: -0.1700

Data Index: 3826732 (Open Web Text)

Max Activating Token Index: 251

Text #6

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.6466. Min Act: -0.1700

Data Index: 1126461 (Open Web Text)

Max Activating Token Index: 800

Text #7

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.6533. Min Act: -0.1700

Data Index: 2231964 (Open Web Text)

Max Activating Token Index: 125

Text #8

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.6400. Min Act: -0.1700

Data Index: 1812244 (Open Web Text)

Max Activating Token Index: 550

Text #9

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.6230. Min Act: -0.1700

Data Index: 7588822 (Open Web Text)

Max Activating Token Index: 843

Text #10

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.6232. Min Act: -0.1700

Data Index: 7686488 (Open Web Text)

Max Activating Token Index: 1012

Text #11

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.6253. Min Act: -0.1700

Data Index: 6174381 (Open Web Text)

Max Activating Token Index: 695

Text #12

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.6086. Min Act: -0.1700

Data Index: 1199698 (Open Web Text)

Max Activating Token Index: 138

Text #13

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.6305. Min Act: -0.1700

Data Index: 4796079 (Open Web Text)

Max Activating Token Index: 1021

Text #14

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.6171. Min Act: -0.1700

Data Index: 6654936 (Open Web Text)

Max Activating Token Index: 581

Text #15

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.6137. Min Act: -0.1700

Data Index: 5991707 (Open Web Text)

Max Activating Token Index: 616

Text #16

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.6093. Min Act: -0.1700

Data Index: 5279717 (Open Web Text)

Max Activating Token Index: 315

Text #17

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.6257. Min Act: -0.1700

Data Index: 1386167 (Open Web Text)

Max Activating Token Index: 598

Text #18

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.6006. Min Act: -0.1700

Data Index: 6984551 (Open Web Text)

Max Activating Token Index: 212

Text #19

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.5773. Min Act: -0.1700

Data Index: 7128753 (Open Web Text)

Max Activating Token Index: 527