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

Dataset: Open Web Text

Neuron 1380 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: 3.7511. Min Range: -3.7511

Max Act: 3.7511. Min Act: -0.1700

Data Index: 8738937 (Open Web Text)

Max Activating Token Index: 129

Text #1

Max Range: 3.7511. Min Range: -3.7511

Max Act: 3.6873. Min Act: -0.1700

Data Index: 4138975 (Open Web Text)

Max Activating Token Index: 540

Text #2

Max Range: 3.7511. Min Range: -3.7511

Max Act: 3.6782. Min Act: -0.1700

Data Index: 5316759 (Open Web Text)

Max Activating Token Index: 702

Text #3

Max Range: 3.7511. Min Range: -3.7511

Max Act: 3.6549. Min Act: -0.1700

Data Index: 5678095 (Open Web Text)

Max Activating Token Index: 38

Text #4

Max Range: 3.7511. Min Range: -3.7511

Max Act: 3.6514. Min Act: -0.1700

Data Index: 1495724 (Open Web Text)

Max Activating Token Index: 794

Text #5

Max Range: 3.7511. Min Range: -3.7511

Max Act: 3.6453. Min Act: -0.1700

Data Index: 3717133 (Open Web Text)

Max Activating Token Index: 568

Text #6

Max Range: 3.7511. Min Range: -3.7511

Max Act: 3.6451. Min Act: -0.1700

Data Index: 5699817 (Open Web Text)

Max Activating Token Index: 301

Text #7

Max Range: 3.7511. Min Range: -3.7511

Max Act: 3.6370. Min Act: -0.1700

Data Index: 3069218 (Open Web Text)

Max Activating Token Index: 103

Text #8

Max Range: 3.7511. Min Range: -3.7511

Max Act: 3.6393. Min Act: -0.1700

Data Index: 7897881 (Open Web Text)

Max Activating Token Index: 365

Text #9

Max Range: 3.7511. Min Range: -3.7511

Max Act: 3.6161. Min Act: -0.1700

Data Index: 8016372 (Open Web Text)

Max Activating Token Index: 821

Text #10

Max Range: 3.7511. Min Range: -3.7511

Max Act: 3.6083. Min Act: -0.1700

Data Index: 4197618 (Open Web Text)

Max Activating Token Index: 143

Text #11

Max Range: 3.7511. Min Range: -3.7511

Max Act: 3.5623. Min Act: -0.1700

Data Index: 408274 (Open Web Text)

Max Activating Token Index: 375

Text #12

Max Range: 3.7511. Min Range: -3.7511

Max Act: 3.5658. Min Act: -0.1700

Data Index: 6231970 (Open Web Text)

Max Activating Token Index: 783

Text #13

Max Range: 3.7511. Min Range: -3.7511

Max Act: 3.5379. Min Act: -0.1700

Data Index: 3653069 (Open Web Text)

Max Activating Token Index: 698

Text #14

Max Range: 3.7511. Min Range: -3.7511

Max Act: 3.5484. Min Act: -0.1700

Data Index: 6972077 (Open Web Text)

Max Activating Token Index: 647

Text #15

Max Range: 3.7511. Min Range: -3.7511

Max Act: 3.5431. Min Act: -0.1700

Data Index: 3264256 (Open Web Text)

Max Activating Token Index: 569

Text #16

Max Range: 3.7511. Min Range: -3.7511

Max Act: 3.5515. Min Act: -0.1700

Data Index: 2510086 (Open Web Text)

Max Activating Token Index: 641

Text #17

Max Range: 3.7511. Min Range: -3.7511

Max Act: 3.5275. Min Act: -0.1700

Data Index: 6131831 (Open Web Text)

Max Activating Token Index: 229

Text #18

Max Range: 3.7511. Min Range: -3.7511

Max Act: 3.5401. Min Act: -0.1700

Data Index: 5929962 (Open Web Text)

Max Activating Token Index: 958

Text #19

Max Range: 3.7511. Min Range: -3.7511

Max Act: 3.5339. Min Act: -0.1700

Data Index: 6141617 (Open Web Text)

Max Activating Token Index: 835