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

Dataset: Open Web Text

Neuron 86 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: 3.3180. Min Range: -3.3180

Max Act: 3.3180. Min Act: -0.1700

Data Index: 7133962 (Open Web Text)

Max Activating Token Index: 266

Text #1

Max Range: 3.3180. Min Range: -3.3180

Max Act: 3.3056. Min Act: -0.1700

Data Index: 209619 (Open Web Text)

Max Activating Token Index: 784

Text #2

Max Range: 3.3180. Min Range: -3.3180

Max Act: 3.1952. Min Act: -0.1700

Data Index: 5916088 (Open Web Text)

Max Activating Token Index: 779

Text #3

Max Range: 3.3180. Min Range: -3.3180

Max Act: 3.1397. Min Act: -0.1700

Data Index: 3442466 (Open Web Text)

Max Activating Token Index: 579

Text #4

Max Range: 3.3180. Min Range: -3.3180

Max Act: 3.0935. Min Act: -0.1700

Data Index: 3021914 (Open Web Text)

Max Activating Token Index: 987

Text #5

Max Range: 3.3180. Min Range: -3.3180

Max Act: 3.0940. Min Act: -0.1700

Data Index: 8470071 (Open Web Text)

Max Activating Token Index: 792

Text #6

Max Range: 3.3180. Min Range: -3.3180

Max Act: 3.0613. Min Act: -0.1700

Data Index: 8784402 (Open Web Text)

Max Activating Token Index: 526

Text #7

Max Range: 3.3180. Min Range: -3.3180

Max Act: 3.0843. Min Act: -0.1700

Data Index: 2095581 (Open Web Text)

Max Activating Token Index: 513

Text #8

Max Range: 3.3180. Min Range: -3.3180

Max Act: 3.0460. Min Act: -0.1700

Data Index: 2024638 (Open Web Text)

Max Activating Token Index: 239

Text #9

Max Range: 3.3180. Min Range: -3.3180

Max Act: 3.0494. Min Act: -0.1700

Data Index: 5494972 (Open Web Text)

Max Activating Token Index: 327

Text #10

Max Range: 3.3180. Min Range: -3.3180

Max Act: 3.0386. Min Act: -0.1700

Data Index: 6343309 (Open Web Text)

Max Activating Token Index: 849

Text #11

Max Range: 3.3180. Min Range: -3.3180

Max Act: 3.0495. Min Act: -0.1700

Data Index: 3470177 (Open Web Text)

Max Activating Token Index: 492

Text #12

Max Range: 3.3180. Min Range: -3.3180

Max Act: 3.0470. Min Act: -0.1700

Data Index: 1510970 (Open Web Text)

Max Activating Token Index: 367

Text #13

Max Range: 3.3180. Min Range: -3.3180

Max Act: 3.0561. Min Act: -0.1700

Data Index: 5002868 (Open Web Text)

Max Activating Token Index: 334

Text #14

Max Range: 3.3180. Min Range: -3.3180

Max Act: 3.0275. Min Act: -0.1700

Data Index: 1770268 (Open Web Text)

Max Activating Token Index: 511

Text #15

Max Range: 3.3180. Min Range: -3.3180

Max Act: 3.0063. Min Act: -0.1700

Data Index: 3503086 (Open Web Text)

Max Activating Token Index: 731

Text #16

Max Range: 3.3180. Min Range: -3.3180

Max Act: 3.0008. Min Act: -0.1700

Data Index: 6359271 (Open Web Text)

Max Activating Token Index: 399

Text #17

Max Range: 3.3180. Min Range: -3.3180

Max Act: 3.0111. Min Act: -0.1700

Data Index: 1447059 (Open Web Text)

Max Activating Token Index: 719

Text #18

Max Range: 3.3180. Min Range: -3.3180

Max Act: 3.0173. Min Act: -0.1700

Data Index: 3922980 (Open Web Text)

Max Activating Token Index: 307

Text #19

Max Range: 3.3180. Min Range: -3.3180

Max Act: 3.0061. Min Act: -0.1700

Data Index: 2753520 (Open Web Text)

Max Activating Token Index: 859