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

Dataset: Open Web Text

Neuron 1462 in Layer 3

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: 3.0529. Min Range: -3.0529

Max Act: 3.0529. Min Act: -0.1700

Data Index: 4661364 (Open Web Text)

Max Activating Token Index: 384

Text #1

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9791. Min Act: -0.1700

Data Index: 3799972 (Open Web Text)

Max Activating Token Index: 326

Text #2

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9739. Min Act: -0.1700

Data Index: 5426885 (Open Web Text)

Max Activating Token Index: 412

Text #3

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9612. Min Act: -0.1700

Data Index: 3370167 (Open Web Text)

Max Activating Token Index: 215

Text #4

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9406. Min Act: -0.1700

Data Index: 4942565 (Open Web Text)

Max Activating Token Index: 151

Text #5

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9456. Min Act: -0.1700

Data Index: 5916227 (Open Web Text)

Max Activating Token Index: 98

Text #6

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9586. Min Act: -0.1700

Data Index: 4384773 (Open Web Text)

Max Activating Token Index: 382

Text #7

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9350. Min Act: -0.1700

Data Index: 3820422 (Open Web Text)

Max Activating Token Index: 123

Text #8

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9202. Min Act: -0.1700

Data Index: 3630555 (Open Web Text)

Max Activating Token Index: 434

Text #9

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9217. Min Act: -0.1700

Data Index: 7180752 (Open Web Text)

Max Activating Token Index: 596

Text #10

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9143. Min Act: -0.1700

Data Index: 2010470 (Open Web Text)

Max Activating Token Index: 427

Text #11

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9238. Min Act: -0.1700

Data Index: 1870955 (Open Web Text)

Max Activating Token Index: 18

Text #12

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9066. Min Act: -0.1700

Data Index: 8473110 (Open Web Text)

Max Activating Token Index: 515

Text #13

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.8988. Min Act: -0.1700

Data Index: 6246615 (Open Web Text)

Max Activating Token Index: 903

Text #14

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9132. Min Act: -0.1700

Data Index: 2245777 (Open Web Text)

Max Activating Token Index: 430

Text #15

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.8832. Min Act: -0.1700

Data Index: 5061491 (Open Web Text)

Max Activating Token Index: 156

Text #16

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9289. Min Act: -0.1700

Data Index: 2267676 (Open Web Text)

Max Activating Token Index: 449

Text #17

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.8857. Min Act: -0.1700

Data Index: 1026931 (Open Web Text)

Max Activating Token Index: 249

Text #18

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.8599. Min Act: -0.1700

Data Index: 4608836 (Open Web Text)

Max Activating Token Index: 969

Text #19

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.8993. Min Act: -0.1700

Data Index: 2021365 (Open Web Text)

Max Activating Token Index: 320