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

Dataset: Open Web Text

Neuron 351 in Layer 2

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: 3.8442. Min Range: -3.8442

Max Act: 3.8442. Min Act: -0.1700

Data Index: 6970656 (Open Web Text)

Max Activating Token Index: 186

Text #1

Max Range: 3.8442. Min Range: -3.8442

Max Act: 3.7814. Min Act: -0.1700

Data Index: 4399211 (Open Web Text)

Max Activating Token Index: 325

Text #2

Max Range: 3.8442. Min Range: -3.8442

Max Act: 3.7746. Min Act: -0.1700

Data Index: 8399821 (Open Web Text)

Max Activating Token Index: 462

Text #3

Max Range: 3.8442. Min Range: -3.8442

Max Act: 3.7995. Min Act: -0.1700

Data Index: 7984424 (Open Web Text)

Max Activating Token Index: 580

Text #4

Max Range: 3.8442. Min Range: -3.8442

Max Act: 3.7556. Min Act: -0.1700

Data Index: 6715962 (Open Web Text)

Max Activating Token Index: 496

Text #5

Max Range: 3.8442. Min Range: -3.8442

Max Act: 3.7728. Min Act: -0.1700

Data Index: 8702533 (Open Web Text)

Max Activating Token Index: 748

Text #6

Max Range: 3.8442. Min Range: -3.8442

Max Act: 3.7436. Min Act: -0.1700

Data Index: 7299347 (Open Web Text)

Max Activating Token Index: 181

Text #7

Max Range: 3.8442. Min Range: -3.8442

Max Act: 3.7421. Min Act: -0.1700

Data Index: 1540759 (Open Web Text)

Max Activating Token Index: 404

Text #8

Max Range: 3.8442. Min Range: -3.8442

Max Act: 3.6957. Min Act: -0.1700

Data Index: 2910749 (Open Web Text)

Max Activating Token Index: 933

Text #9

Max Range: 3.8442. Min Range: -3.8442

Max Act: 3.6899. Min Act: -0.1700

Data Index: 8603458 (Open Web Text)

Max Activating Token Index: 107

Text #10

Max Range: 3.8442. Min Range: -3.8442

Max Act: 3.7024. Min Act: -0.1700

Data Index: 872062 (Open Web Text)

Max Activating Token Index: 536

Text #11

Max Range: 3.8442. Min Range: -3.8442

Max Act: 3.6698. Min Act: -0.1700

Data Index: 7599973 (Open Web Text)

Max Activating Token Index: 734

Text #12

Max Range: 3.8442. Min Range: -3.8442

Max Act: 3.6637. Min Act: -0.1700

Data Index: 1763185 (Open Web Text)

Max Activating Token Index: 685

Text #13

Max Range: 3.8442. Min Range: -3.8442

Max Act: 3.6590. Min Act: -0.1700

Data Index: 267594 (Open Web Text)

Max Activating Token Index: 356

Text #14

Max Range: 3.8442. Min Range: -3.8442

Max Act: 3.6664. Min Act: -0.1700

Data Index: 5141533 (Open Web Text)

Max Activating Token Index: 226

Text #15

Max Range: 3.8442. Min Range: -3.8442

Max Act: 3.6377. Min Act: -0.1700

Data Index: 5946247 (Open Web Text)

Max Activating Token Index: 474

Text #16

Max Range: 3.8442. Min Range: -3.8442

Max Act: 3.6344. Min Act: -0.1700

Data Index: 3698356 (Open Web Text)

Max Activating Token Index: 36

Text #17

Max Range: 3.8442. Min Range: -3.8442

Max Act: 3.6421. Min Act: -0.1700

Data Index: 165519 (Open Web Text)

Max Activating Token Index: 400

Text #18

Max Range: 3.8442. Min Range: -3.8442

Max Act: 3.6098. Min Act: -0.1700

Data Index: 947156 (Open Web Text)

Max Activating Token Index: 448

Text #19

Max Range: 3.8442. Min Range: -3.8442

Max Act: 3.6143. Min Act: -0.1700

Data Index: 2311611 (Open Web Text)

Max Activating Token Index: 653