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

Dataset: Open Web Text

Neuron 1593 in Layer 6

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: 4.7537. Min Range: -4.7537

Max Act: 4.7537. Min Act: -0.1700

Data Index: 6013200 (Open Web Text)

Max Activating Token Index: 654

Text #1

Max Range: 4.7537. Min Range: -4.7537

Max Act: 4.6467. Min Act: -0.1700

Data Index: 7898919 (Open Web Text)

Max Activating Token Index: 955

Text #2

Max Range: 4.7537. Min Range: -4.7537

Max Act: 4.6299. Min Act: -0.1700

Data Index: 5888456 (Open Web Text)

Max Activating Token Index: 242

Text #3

Max Range: 4.7537. Min Range: -4.7537

Max Act: 4.6233. Min Act: -0.1700

Data Index: 4276411 (Open Web Text)

Max Activating Token Index: 545

Text #4

Max Range: 4.7537. Min Range: -4.7537

Max Act: 4.5760. Min Act: -0.1700

Data Index: 1359096 (Open Web Text)

Max Activating Token Index: 15

Text #5

Max Range: 4.7537. Min Range: -4.7537

Max Act: 4.5836. Min Act: -0.1700

Data Index: 5566988 (Open Web Text)

Max Activating Token Index: 704

Text #6

Max Range: 4.7537. Min Range: -4.7537

Max Act: 4.5767. Min Act: -0.1700

Data Index: 2397394 (Open Web Text)

Max Activating Token Index: 253

Text #7

Max Range: 4.7537. Min Range: -4.7537

Max Act: 4.5932. Min Act: -0.1700

Data Index: 2167561 (Open Web Text)

Max Activating Token Index: 458

Text #8

Max Range: 4.7537. Min Range: -4.7537

Max Act: 4.5713. Min Act: -0.1700

Data Index: 7106096 (Open Web Text)

Max Activating Token Index: 352

Text #9

Max Range: 4.7537. Min Range: -4.7537

Max Act: 4.5820. Min Act: -0.1700

Data Index: 960163 (Open Web Text)

Max Activating Token Index: 731

Text #10

Max Range: 4.7537. Min Range: -4.7537

Max Act: 4.5731. Min Act: -0.1700

Data Index: 2554514 (Open Web Text)

Max Activating Token Index: 36

Text #11

Max Range: 4.7537. Min Range: -4.7537

Max Act: 4.5021. Min Act: -0.1700

Data Index: 8387113 (Open Web Text)

Max Activating Token Index: 124

Text #12

Max Range: 4.7537. Min Range: -4.7537

Max Act: 4.5133. Min Act: -0.1700

Data Index: 6933814 (Open Web Text)

Max Activating Token Index: 352

Text #13

Max Range: 4.7537. Min Range: -4.7537

Max Act: 4.4835. Min Act: -0.1700

Data Index: 1314031 (Open Web Text)

Max Activating Token Index: 438

Text #14

Max Range: 4.7537. Min Range: -4.7537

Max Act: 4.5030. Min Act: -0.1700

Data Index: 224221 (Open Web Text)

Max Activating Token Index: 192

Text #15

Max Range: 4.7537. Min Range: -4.7537

Max Act: 4.5093. Min Act: -0.1700

Data Index: 1572288 (Open Web Text)

Max Activating Token Index: 277

Text #16

Max Range: 4.7537. Min Range: -4.7537

Max Act: 4.5203. Min Act: -0.1700

Data Index: 8069919 (Open Web Text)

Max Activating Token Index: 450

Text #17

Max Range: 4.7537. Min Range: -4.7537

Max Act: 4.4822. Min Act: -0.1700

Data Index: 3063920 (Open Web Text)

Max Activating Token Index: 636

Text #18

Max Range: 4.7537. Min Range: -4.7537

Max Act: 4.4789. Min Act: -0.1700

Data Index: 5293229 (Open Web Text)

Max Activating Token Index: 555

Text #19

Max Range: 4.7537. Min Range: -4.7537

Max Act: 4.4587. Min Act: -0.1700

Data Index: 5476053 (Open Web Text)

Max Activating Token Index: 959