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

Dataset: Open Web Text

Neuron 1443 in Layer 1

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: 4.4891. Min Range: -4.4891

Max Act: 4.4834. Min Act: -0.1700

Data Index: 7739648 (Open Web Text)

Max Activating Token Index: 498

Text #1

Max Range: 4.4891. Min Range: -4.4891

Max Act: 4.4689. Min Act: -0.1700

Data Index: 4238498 (Open Web Text)

Max Activating Token Index: 221

Text #2

Max Range: 4.4891. Min Range: -4.4891

Max Act: 4.4891. Min Act: -0.1700

Data Index: 2319285 (Open Web Text)

Max Activating Token Index: 143

Text #3

Max Range: 4.4891. Min Range: -4.4891

Max Act: 4.4548. Min Act: -0.1700

Data Index: 3152688 (Open Web Text)

Max Activating Token Index: 111

Text #4

Max Range: 4.4891. Min Range: -4.4891

Max Act: 4.4536. Min Act: -0.1700

Data Index: 3289084 (Open Web Text)

Max Activating Token Index: 450

Text #5

Max Range: 4.4891. Min Range: -4.4891

Max Act: 4.4471. Min Act: -0.1700

Data Index: 713649 (Open Web Text)

Max Activating Token Index: 915

Text #6

Max Range: 4.4891. Min Range: -4.4891

Max Act: 4.4417. Min Act: -0.1700

Data Index: 715312 (Open Web Text)

Max Activating Token Index: 196

Text #7

Max Range: 4.4891. Min Range: -4.4891

Max Act: 4.4720. Min Act: -0.1700

Data Index: 1643732 (Open Web Text)

Max Activating Token Index: 668

Text #8

Max Range: 4.4891. Min Range: -4.4891

Max Act: 4.4604. Min Act: -0.1700

Data Index: 8777499 (Open Web Text)

Max Activating Token Index: 170

Text #9

Max Range: 4.4891. Min Range: -4.4891

Max Act: 4.4764. Min Act: -0.1700

Data Index: 6934650 (Open Web Text)

Max Activating Token Index: 198

Text #10

Max Range: 4.4891. Min Range: -4.4891

Max Act: 4.4709. Min Act: -0.1700

Data Index: 5546026 (Open Web Text)

Max Activating Token Index: 119

Text #11

Max Range: 4.4891. Min Range: -4.4891

Max Act: 4.4062. Min Act: -0.1700

Data Index: 2529688 (Open Web Text)

Max Activating Token Index: 294

Text #12

Max Range: 4.4891. Min Range: -4.4891

Max Act: 4.4344. Min Act: -0.1700

Data Index: 5691994 (Open Web Text)

Max Activating Token Index: 123

Text #13

Max Range: 4.4891. Min Range: -4.4891

Max Act: 4.4047. Min Act: -0.1700

Data Index: 5261842 (Open Web Text)

Max Activating Token Index: 611

Text #14

Max Range: 4.4891. Min Range: -4.4891

Max Act: 4.4300. Min Act: -0.1700

Data Index: 4894776 (Open Web Text)

Max Activating Token Index: 458

Text #15

Max Range: 4.4891. Min Range: -4.4891

Max Act: 4.4183. Min Act: -0.1700

Data Index: 4859407 (Open Web Text)

Max Activating Token Index: 325

Text #16

Max Range: 4.4891. Min Range: -4.4891

Max Act: 4.4288. Min Act: -0.1700

Data Index: 800081 (Open Web Text)

Max Activating Token Index: 425

Text #17

Max Range: 4.4891. Min Range: -4.4891

Max Act: 4.4205. Min Act: -0.1700

Data Index: 4549454 (Open Web Text)

Max Activating Token Index: 451

Text #18

Max Range: 4.4891. Min Range: -4.4891

Max Act: 4.4395. Min Act: -0.1700

Data Index: 417180 (Open Web Text)

Max Activating Token Index: 484

Text #19

Max Range: 4.4891. Min Range: -4.4891

Max Act: 4.4165. Min Act: -0.1700

Data Index: 4483691 (Open Web Text)

Max Activating Token Index: 616