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

Dataset: Open Web Text

Neuron 983 in Layer 4

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: 3.5259. Min Range: -3.5259

Max Act: 3.5259. Min Act: -0.1700

Data Index: 1967911 (Open Web Text)

Max Activating Token Index: 948

Text #1

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.5240. Min Act: -0.1700

Data Index: 4055008 (Open Web Text)

Max Activating Token Index: 877

Text #2

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.4942. Min Act: -0.1700

Data Index: 1072511 (Open Web Text)

Max Activating Token Index: 909

Text #3

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.4725. Min Act: -0.1700

Data Index: 8008680 (Open Web Text)

Max Activating Token Index: 790

Text #4

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.4731. Min Act: -0.1700

Data Index: 6003630 (Open Web Text)

Max Activating Token Index: 712

Text #5

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.4734. Min Act: -0.1700

Data Index: 2766584 (Open Web Text)

Max Activating Token Index: 383

Text #6

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.4902. Min Act: -0.1700

Data Index: 1180630 (Open Web Text)

Max Activating Token Index: 250

Text #7

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.4778. Min Act: -0.1700

Data Index: 765942 (Open Web Text)

Max Activating Token Index: 351

Text #8

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.4630. Min Act: -0.1700

Data Index: 3741439 (Open Web Text)

Max Activating Token Index: 315

Text #9

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.4497. Min Act: -0.1700

Data Index: 3952043 (Open Web Text)

Max Activating Token Index: 488

Text #10

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.4468. Min Act: -0.1700

Data Index: 4563725 (Open Web Text)

Max Activating Token Index: 230

Text #11

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.4577. Min Act: -0.1700

Data Index: 7195000 (Open Web Text)

Max Activating Token Index: 115

Text #12

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.4448. Min Act: -0.1700

Data Index: 147274 (Open Web Text)

Max Activating Token Index: 1003

Text #13

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.4474. Min Act: -0.1700

Data Index: 6419565 (Open Web Text)

Max Activating Token Index: 390

Text #14

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.4447. Min Act: -0.1700

Data Index: 5615008 (Open Web Text)

Max Activating Token Index: 642

Text #15

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.4534. Min Act: -0.1700

Data Index: 656763 (Open Web Text)

Max Activating Token Index: 719

Text #16

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.4581. Min Act: -0.1700

Data Index: 4843593 (Open Web Text)

Max Activating Token Index: 636

Text #17

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.4328. Min Act: -0.1700

Data Index: 906499 (Open Web Text)

Max Activating Token Index: 798

Text #18

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.4234. Min Act: -0.1700

Data Index: 5500666 (Open Web Text)

Max Activating Token Index: 694

Text #19

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.4309. Min Act: -0.1700

Data Index: 2797788 (Open Web Text)

Max Activating Token Index: 745