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

Dataset: Open Web Text

Neuron 2921 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: 3.6986. Min Range: -3.6986

Max Act: 3.6986. Min Act: -0.1700

Data Index: 7457710 (Open Web Text)

Max Activating Token Index: 227

Text #1

Max Range: 3.6986. Min Range: -3.6986

Max Act: 3.5804. Min Act: -0.1700

Data Index: 7298553 (Open Web Text)

Max Activating Token Index: 766

Text #2

Max Range: 3.6986. Min Range: -3.6986

Max Act: 3.5869. Min Act: -0.1700

Data Index: 6978247 (Open Web Text)

Max Activating Token Index: 817

Text #3

Max Range: 3.6986. Min Range: -3.6986

Max Act: 3.5314. Min Act: -0.1700

Data Index: 2982750 (Open Web Text)

Max Activating Token Index: 288

Text #4

Max Range: 3.6986. Min Range: -3.6986

Max Act: 3.5565. Min Act: -0.1700

Data Index: 686278 (Open Web Text)

Max Activating Token Index: 309

Text #5

Max Range: 3.6986. Min Range: -3.6986

Max Act: 3.5297. Min Act: -0.1700

Data Index: 4658789 (Open Web Text)

Max Activating Token Index: 254

Text #6

Max Range: 3.6986. Min Range: -3.6986

Max Act: 3.5270. Min Act: -0.1700

Data Index: 5526668 (Open Web Text)

Max Activating Token Index: 160

Text #7

Max Range: 3.6986. Min Range: -3.6986

Max Act: 3.5028. Min Act: -0.1700

Data Index: 3501580 (Open Web Text)

Max Activating Token Index: 80

Text #8

Max Range: 3.6986. Min Range: -3.6986

Max Act: 3.5121. Min Act: -0.1700

Data Index: 4731812 (Open Web Text)

Max Activating Token Index: 532

Text #9

Max Range: 3.6986. Min Range: -3.6986

Max Act: 3.5123. Min Act: -0.1700

Data Index: 4347698 (Open Web Text)

Max Activating Token Index: 927

Text #10

Max Range: 3.6986. Min Range: -3.6986

Max Act: 3.5270. Min Act: -0.1700

Data Index: 7692901 (Open Web Text)

Max Activating Token Index: 794

Text #11

Max Range: 3.6986. Min Range: -3.6986

Max Act: 3.4696. Min Act: -0.1700

Data Index: 4498112 (Open Web Text)

Max Activating Token Index: 411

Text #12

Max Range: 3.6986. Min Range: -3.6986

Max Act: 3.4877. Min Act: -0.1700

Data Index: 2926011 (Open Web Text)

Max Activating Token Index: 379

Text #13

Max Range: 3.6986. Min Range: -3.6986

Max Act: 3.4983. Min Act: -0.1700

Data Index: 6823863 (Open Web Text)

Max Activating Token Index: 200

Text #14

Max Range: 3.6986. Min Range: -3.6986

Max Act: 3.4642. Min Act: -0.1700

Data Index: 3009585 (Open Web Text)

Max Activating Token Index: 624

Text #15

Max Range: 3.6986. Min Range: -3.6986

Max Act: 3.4490. Min Act: -0.1700

Data Index: 1366986 (Open Web Text)

Max Activating Token Index: 257

Text #16

Max Range: 3.6986. Min Range: -3.6986

Max Act: 3.4625. Min Act: -0.1700

Data Index: 2604373 (Open Web Text)

Max Activating Token Index: 332

Text #17

Max Range: 3.6986. Min Range: -3.6986

Max Act: 3.4678. Min Act: -0.1700

Data Index: 2716757 (Open Web Text)

Max Activating Token Index: 88

Text #18

Max Range: 3.6986. Min Range: -3.6986

Max Act: 3.4491. Min Act: -0.1700

Data Index: 1005649 (Open Web Text)

Max Activating Token Index: 254

Text #19

Max Range: 3.6986. Min Range: -3.6986

Max Act: 3.4446. Min Act: -0.1700

Data Index: 3943218 (Open Web Text)

Max Activating Token Index: 579