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

Dataset: Open Web Text

Neuron 38 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: 4.6585. Min Range: -4.6585

Max Act: 4.6585. Min Act: -0.1700

Data Index: 1210055 (Open Web Text)

Max Activating Token Index: 39

Text #1

Max Range: 4.6585. Min Range: -4.6585

Max Act: 4.4605. Min Act: -0.1700

Data Index: 4616107 (Open Web Text)

Max Activating Token Index: 241

Text #2

Max Range: 4.6585. Min Range: -4.6585

Max Act: 4.3733. Min Act: -0.1700

Data Index: 8567403 (Open Web Text)

Max Activating Token Index: 140

Text #3

Max Range: 4.6585. Min Range: -4.6585

Max Act: 4.3691. Min Act: -0.1700

Data Index: 7066907 (Open Web Text)

Max Activating Token Index: 32

Text #4

Max Range: 4.6585. Min Range: -4.6585

Max Act: 4.3080. Min Act: -0.1700

Data Index: 271752 (Open Web Text)

Max Activating Token Index: 339

Text #5

Max Range: 4.6585. Min Range: -4.6585

Max Act: 4.3244. Min Act: -0.1700

Data Index: 1376732 (Open Web Text)

Max Activating Token Index: 359

Text #6

Max Range: 4.6585. Min Range: -4.6585

Max Act: 4.2967. Min Act: -0.1700

Data Index: 2422156 (Open Web Text)

Max Activating Token Index: 25

Text #7

Max Range: 4.6585. Min Range: -4.6585

Max Act: 4.2319. Min Act: -0.1700

Data Index: 3736443 (Open Web Text)

Max Activating Token Index: 57

Text #8

Max Range: 4.6585. Min Range: -4.6585

Max Act: 4.2643. Min Act: -0.1700

Data Index: 7961716 (Open Web Text)

Max Activating Token Index: 83

Text #9

Max Range: 4.6585. Min Range: -4.6585

Max Act: 4.2039. Min Act: -0.1700

Data Index: 4112021 (Open Web Text)

Max Activating Token Index: 236

Text #10

Max Range: 4.6585. Min Range: -4.6585

Max Act: 4.1832. Min Act: -0.1700

Data Index: 5922927 (Open Web Text)

Max Activating Token Index: 284

Text #11

Max Range: 4.6585. Min Range: -4.6585

Max Act: 4.2433. Min Act: -0.1700

Data Index: 3918080 (Open Web Text)

Max Activating Token Index: 16

Text #12

Max Range: 4.6585. Min Range: -4.6585

Max Act: 4.2218. Min Act: -0.1700

Data Index: 6560631 (Open Web Text)

Max Activating Token Index: 1019

Text #13

Max Range: 4.6585. Min Range: -4.6585

Max Act: 4.1926. Min Act: -0.1700

Data Index: 3562248 (Open Web Text)

Max Activating Token Index: 277

Text #14

Max Range: 4.6585. Min Range: -4.6585

Max Act: 4.1799. Min Act: -0.1700

Data Index: 7764844 (Open Web Text)

Max Activating Token Index: 151

Text #15

Max Range: 4.6585. Min Range: -4.6585

Max Act: 4.1722. Min Act: -0.1700

Data Index: 4572540 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 4.6585. Min Range: -4.6585

Max Act: 4.1891. Min Act: -0.1700

Data Index: 1538348 (Open Web Text)

Max Activating Token Index: 164

Text #17

Max Range: 4.6585. Min Range: -4.6585

Max Act: 4.1968. Min Act: -0.1700

Data Index: 565700 (Open Web Text)

Max Activating Token Index: 662

Text #18

Max Range: 4.6585. Min Range: -4.6585

Max Act: 4.1817. Min Act: -0.1700

Data Index: 2743331 (Open Web Text)

Max Activating Token Index: 241

Text #19

Max Range: 4.6585. Min Range: -4.6585

Max Act: 4.1947. Min Act: -0.1700

Data Index: 4954556 (Open Web Text)

Max Activating Token Index: 729