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

Dataset: Open Web Text

Neuron 618 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: 4.8389. Min Range: -4.8389

Max Act: 4.8389. Min Act: -0.1700

Data Index: 5985011 (Open Web Text)

Max Activating Token Index: 418

Text #1

Max Range: 4.8389. Min Range: -4.8389

Max Act: 4.6772. Min Act: -0.1700

Data Index: 4676261 (Open Web Text)

Max Activating Token Index: 438

Text #2

Max Range: 4.8389. Min Range: -4.8389

Max Act: 4.6397. Min Act: -0.1700

Data Index: 7545365 (Open Web Text)

Max Activating Token Index: 719

Text #3

Max Range: 4.8389. Min Range: -4.8389

Max Act: 4.6074. Min Act: -0.1700

Data Index: 513983 (Open Web Text)

Max Activating Token Index: 689

Text #4

Max Range: 4.8389. Min Range: -4.8389

Max Act: 4.5986. Min Act: -0.1700

Data Index: 4254931 (Open Web Text)

Max Activating Token Index: 752

Text #5

Max Range: 4.8389. Min Range: -4.8389

Max Act: 4.5867. Min Act: -0.1700

Data Index: 2778047 (Open Web Text)

Max Activating Token Index: 120

Text #6

Max Range: 4.8389. Min Range: -4.8389

Max Act: 4.5647. Min Act: -0.1700

Data Index: 1737695 (Open Web Text)

Max Activating Token Index: 687

Text #7

Max Range: 4.8389. Min Range: -4.8389

Max Act: 4.5550. Min Act: -0.1700

Data Index: 5174806 (Open Web Text)

Max Activating Token Index: 500

Text #8

Max Range: 4.8389. Min Range: -4.8389

Max Act: 4.5323. Min Act: -0.1700

Data Index: 1465767 (Open Web Text)

Max Activating Token Index: 69

Text #9

Max Range: 4.8389. Min Range: -4.8389

Max Act: 4.5057. Min Act: -0.1700

Data Index: 4031997 (Open Web Text)

Max Activating Token Index: 163

Text #10

Max Range: 4.8389. Min Range: -4.8389

Max Act: 4.5064. Min Act: -0.1700

Data Index: 3277843 (Open Web Text)

Max Activating Token Index: 659

Text #11

Max Range: 4.8389. Min Range: -4.8389

Max Act: 4.4596. Min Act: -0.1700

Data Index: 5915658 (Open Web Text)

Max Activating Token Index: 356

Text #12

Max Range: 4.8389. Min Range: -4.8389

Max Act: 4.4826. Min Act: -0.1700

Data Index: 5731547 (Open Web Text)

Max Activating Token Index: 745

Text #13

Max Range: 4.8389. Min Range: -4.8389

Max Act: 4.4659. Min Act: -0.1700

Data Index: 8268866 (Open Web Text)

Max Activating Token Index: 484

Text #14

Max Range: 4.8389. Min Range: -4.8389

Max Act: 4.4250. Min Act: -0.1700

Data Index: 6465219 (Open Web Text)

Max Activating Token Index: 977

Text #15

Max Range: 4.8389. Min Range: -4.8389

Max Act: 4.4454. Min Act: -0.1700

Data Index: 5367087 (Open Web Text)

Max Activating Token Index: 375

Text #16

Max Range: 4.8389. Min Range: -4.8389

Max Act: 4.4501. Min Act: -0.1700

Data Index: 225451 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 4.8389. Min Range: -4.8389

Max Act: 4.4337. Min Act: -0.1700

Data Index: 2681023 (Open Web Text)

Max Activating Token Index: 557

Text #18

Max Range: 4.8389. Min Range: -4.8389

Max Act: 4.4212. Min Act: -0.1700

Data Index: 4175970 (Open Web Text)

Max Activating Token Index: 953

Text #19

Max Range: 4.8389. Min Range: -4.8389

Max Act: 4.4069. Min Act: -0.1700

Data Index: 7156933 (Open Web Text)

Max Activating Token Index: 2