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

Dataset: Open Web Text

Neuron 260 in Layer 2

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: 1.7857. Min Range: -1.7857

Max Act: 1.7857. Min Act: -0.1700

Data Index: 5681148 (Open Web Text)

Max Activating Token Index: 523

Text #1

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.7740. Min Act: -0.1681

Data Index: 6049245 (Open Web Text)

Max Activating Token Index: 916

Text #2

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.7697. Min Act: -0.1700

Data Index: 5432217 (Open Web Text)

Max Activating Token Index: 548

Text #3

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.7494. Min Act: -0.1697

Data Index: 8103925 (Open Web Text)

Max Activating Token Index: 501

Text #4

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.7612. Min Act: -0.1700

Data Index: 4413106 (Open Web Text)

Max Activating Token Index: 520

Text #5

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.7638. Min Act: -0.1649

Data Index: 8642941 (Open Web Text)

Max Activating Token Index: 60

Text #6

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.7403. Min Act: -0.1700

Data Index: 8800936 (Open Web Text)

Max Activating Token Index: 901

Text #7

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.7451. Min Act: -0.1694

Data Index: 5687273 (Open Web Text)

Max Activating Token Index: 31

Text #8

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.7462. Min Act: -0.1697

Data Index: 3571317 (Open Web Text)

Max Activating Token Index: 899

Text #9

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.7382. Min Act: -0.1698

Data Index: 1811432 (Open Web Text)

Max Activating Token Index: 545

Text #10

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.7216. Min Act: -0.1692

Data Index: 3461312 (Open Web Text)

Max Activating Token Index: 575

Text #11

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.7376. Min Act: -0.1700

Data Index: 6049243 (Open Web Text)

Max Activating Token Index: 544

Text #12

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.7200. Min Act: -0.1699

Data Index: 784465 (Open Web Text)

Max Activating Token Index: 979

Text #13

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.7151. Min Act: -0.1691

Data Index: 6049242 (Open Web Text)

Max Activating Token Index: 915

Text #14

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.7071. Min Act: -0.1700

Data Index: 5661396 (Open Web Text)

Max Activating Token Index: 370

Text #15

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.7144. Min Act: -0.1683

Data Index: 6049238 (Open Web Text)

Max Activating Token Index: 457

Text #16

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.7066. Min Act: -0.1700

Data Index: 5739739 (Open Web Text)

Max Activating Token Index: 477

Text #17

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.6923. Min Act: -0.1695

Data Index: 6032094 (Open Web Text)

Max Activating Token Index: 71

Text #18

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.6857. Min Act: -0.1692

Data Index: 7146273 (Open Web Text)

Max Activating Token Index: 651

Text #19

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.6923. Min Act: -0.1691

Data Index: 1028390 (Open Web Text)

Max Activating Token Index: 815