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

Dataset: Open Web Text

Neuron 156 in Layer 4

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: 3.2852. Min Range: -3.2852

Max Act: 3.2852. Min Act: -0.1700

Data Index: 8188887 (Open Web Text)

Max Activating Token Index: 886

Text #1

Max Range: 3.2852. Min Range: -3.2852

Max Act: 3.2436. Min Act: -0.1700

Data Index: 4882582 (Open Web Text)

Max Activating Token Index: 311

Text #2

Max Range: 3.2852. Min Range: -3.2852

Max Act: 3.2316. Min Act: -0.1700

Data Index: 7054451 (Open Web Text)

Max Activating Token Index: 959

Text #3

Max Range: 3.2852. Min Range: -3.2852

Max Act: 3.1268. Min Act: -0.1700

Data Index: 7099639 (Open Web Text)

Max Activating Token Index: 498

Text #4

Max Range: 3.2852. Min Range: -3.2852

Max Act: 3.1370. Min Act: -0.1700

Data Index: 2554580 (Open Web Text)

Max Activating Token Index: 877

Text #5

Max Range: 3.2852. Min Range: -3.2852

Max Act: 3.1130. Min Act: -0.1700

Data Index: 3024216 (Open Web Text)

Max Activating Token Index: 177

Text #6

Max Range: 3.2852. Min Range: -3.2852

Max Act: 3.1087. Min Act: -0.1700

Data Index: 214575 (Open Web Text)

Max Activating Token Index: 225

Text #7

Max Range: 3.2852. Min Range: -3.2852

Max Act: 3.0881. Min Act: -0.1700

Data Index: 6287911 (Open Web Text)

Max Activating Token Index: 422

Text #8

Max Range: 3.2852. Min Range: -3.2852

Max Act: 3.0388. Min Act: -0.1700

Data Index: 1674144 (Open Web Text)

Max Activating Token Index: 858

Text #9

Max Range: 3.2852. Min Range: -3.2852

Max Act: 3.0336. Min Act: -0.1700

Data Index: 3047076 (Open Web Text)

Max Activating Token Index: 770

Text #10

Max Range: 3.2852. Min Range: -3.2852

Max Act: 3.0140. Min Act: -0.1700

Data Index: 4385888 (Open Web Text)

Max Activating Token Index: 854

Text #11

Max Range: 3.2852. Min Range: -3.2852

Max Act: 3.0186. Min Act: -0.1700

Data Index: 2674709 (Open Web Text)

Max Activating Token Index: 573

Text #12

Max Range: 3.2852. Min Range: -3.2852

Max Act: 2.9967. Min Act: -0.1700

Data Index: 8349600 (Open Web Text)

Max Activating Token Index: 1004

Text #13

Max Range: 3.2852. Min Range: -3.2852

Max Act: 3.0111. Min Act: -0.1700

Data Index: 907425 (Open Web Text)

Max Activating Token Index: 340

Text #14

Max Range: 3.2852. Min Range: -3.2852

Max Act: 3.0123. Min Act: -0.1700

Data Index: 6996377 (Open Web Text)

Max Activating Token Index: 719

Text #15

Max Range: 3.2852. Min Range: -3.2852

Max Act: 2.9740. Min Act: -0.1700

Data Index: 6017991 (Open Web Text)

Max Activating Token Index: 626

Text #16

Max Range: 3.2852. Min Range: -3.2852

Max Act: 2.9832. Min Act: -0.1700

Data Index: 1193491 (Open Web Text)

Max Activating Token Index: 790

Text #17

Max Range: 3.2852. Min Range: -3.2852

Max Act: 2.9680. Min Act: -0.1700

Data Index: 4305603 (Open Web Text)

Max Activating Token Index: 925

Text #18

Max Range: 3.2852. Min Range: -3.2852

Max Act: 2.9883. Min Act: -0.1700

Data Index: 518572 (Open Web Text)

Max Activating Token Index: 442

Text #19

Max Range: 3.2852. Min Range: -3.2852

Max Act: 2.9958. Min Act: -0.1700

Data Index: 496372 (Open Web Text)

Max Activating Token Index: 416