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

Dataset: Open Web Text

Neuron 73 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: 5.3222. Min Range: -5.3222

Max Act: 5.3222. Min Act: -0.1700

Data Index: 122036 (Open Web Text)

Max Activating Token Index: 761

Text #1

Max Range: 5.3222. Min Range: -5.3222

Max Act: 5.3129. Min Act: -0.1700

Data Index: 4018510 (Open Web Text)

Max Activating Token Index: 457

Text #2

Max Range: 5.3222. Min Range: -5.3222

Max Act: 5.2659. Min Act: -0.1700

Data Index: 5269134 (Open Web Text)

Max Activating Token Index: 683

Text #3

Max Range: 5.3222. Min Range: -5.3222

Max Act: 5.1623. Min Act: -0.1700

Data Index: 7166123 (Open Web Text)

Max Activating Token Index: 517

Text #4

Max Range: 5.3222. Min Range: -5.3222

Max Act: 5.0978. Min Act: -0.1700

Data Index: 972062 (Open Web Text)

Max Activating Token Index: 191

Text #5

Max Range: 5.3222. Min Range: -5.3222

Max Act: 5.0621. Min Act: -0.1700

Data Index: 1557861 (Open Web Text)

Max Activating Token Index: 121

Text #6

Max Range: 5.3222. Min Range: -5.3222

Max Act: 5.0356. Min Act: -0.1700

Data Index: 3094009 (Open Web Text)

Max Activating Token Index: 385

Text #7

Max Range: 5.3222. Min Range: -5.3222

Max Act: 5.0691. Min Act: -0.1700

Data Index: 122022 (Open Web Text)

Max Activating Token Index: 834

Text #8

Max Range: 5.3222. Min Range: -5.3222

Max Act: 5.0509. Min Act: -0.1700

Data Index: 4971826 (Open Web Text)

Max Activating Token Index: 514

Text #9

Max Range: 5.3222. Min Range: -5.3222

Max Act: 5.0370. Min Act: -0.1700

Data Index: 3920830 (Open Web Text)

Max Activating Token Index: 134

Text #10

Max Range: 5.3222. Min Range: -5.3222

Max Act: 5.0166. Min Act: -0.1700

Data Index: 1940368 (Open Web Text)

Max Activating Token Index: 215

Text #11

Max Range: 5.3222. Min Range: -5.3222

Max Act: 4.9994. Min Act: -0.1700

Data Index: 5199972 (Open Web Text)

Max Activating Token Index: 281

Text #12

Max Range: 5.3222. Min Range: -5.3222

Max Act: 4.9796. Min Act: -0.1700

Data Index: 3299105 (Open Web Text)

Max Activating Token Index: 649

Text #13

Max Range: 5.3222. Min Range: -5.3222

Max Act: 5.0138. Min Act: -0.1700

Data Index: 7549703 (Open Web Text)

Max Activating Token Index: 701

Text #14

Max Range: 5.3222. Min Range: -5.3222

Max Act: 4.9671. Min Act: -0.1700

Data Index: 1373336 (Open Web Text)

Max Activating Token Index: 425

Text #15

Max Range: 5.3222. Min Range: -5.3222

Max Act: 4.9456. Min Act: -0.1700

Data Index: 3068475 (Open Web Text)

Max Activating Token Index: 617

Text #16

Max Range: 5.3222. Min Range: -5.3222

Max Act: 4.9672. Min Act: -0.1700

Data Index: 5970557 (Open Web Text)

Max Activating Token Index: 376

Text #17

Max Range: 5.3222. Min Range: -5.3222

Max Act: 4.8907. Min Act: -0.1700

Data Index: 6305363 (Open Web Text)

Max Activating Token Index: 273

Text #18

Max Range: 5.3222. Min Range: -5.3222

Max Act: 4.9266. Min Act: -0.1700

Data Index: 2254629 (Open Web Text)

Max Activating Token Index: 421

Text #19

Max Range: 5.3222. Min Range: -5.3222

Max Act: 4.9204. Min Act: -0.1700

Data Index: 2869964 (Open Web Text)

Max Activating Token Index: 326