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

Dataset: Open Web Text

Neuron 1862 in Layer 1

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: 3.6713. Min Range: -3.6713

Max Act: 3.6660. Min Act: -0.1700

Data Index: 863338 (Open Web Text)

Max Activating Token Index: 80

Text #1

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.6456. Min Act: -0.1700

Data Index: 6310877 (Open Web Text)

Max Activating Token Index: 453

Text #2

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.6490. Min Act: -0.1700

Data Index: 6742845 (Open Web Text)

Max Activating Token Index: 510

Text #3

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.6421. Min Act: -0.1700

Data Index: 7016400 (Open Web Text)

Max Activating Token Index: 317

Text #4

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.6713. Min Act: -0.1700

Data Index: 4879899 (Open Web Text)

Max Activating Token Index: 161

Text #5

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.6540. Min Act: -0.1700

Data Index: 3741616 (Open Web Text)

Max Activating Token Index: 253

Text #6

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.6374. Min Act: -0.1700

Data Index: 2454145 (Open Web Text)

Max Activating Token Index: 528

Text #7

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.6119. Min Act: -0.1700

Data Index: 2666641 (Open Web Text)

Max Activating Token Index: 222

Text #8

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.6250. Min Act: -0.1700

Data Index: 5785351 (Open Web Text)

Max Activating Token Index: 570

Text #9

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.6237. Min Act: -0.1700

Data Index: 961096 (Open Web Text)

Max Activating Token Index: 137

Text #10

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.6059. Min Act: -0.1700

Data Index: 3963496 (Open Web Text)

Max Activating Token Index: 917

Text #11

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.6089. Min Act: -0.1700

Data Index: 6057275 (Open Web Text)

Max Activating Token Index: 148

Text #12

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.6027. Min Act: -0.1700

Data Index: 1117712 (Open Web Text)

Max Activating Token Index: 438

Text #13

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.6258. Min Act: -0.1700

Data Index: 1474636 (Open Web Text)

Max Activating Token Index: 524

Text #14

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.6055. Min Act: -0.1700

Data Index: 2942065 (Open Web Text)

Max Activating Token Index: 424

Text #15

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.6150. Min Act: -0.1700

Data Index: 3155400 (Open Web Text)

Max Activating Token Index: 406

Text #16

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.6007. Min Act: -0.1700

Data Index: 2689339 (Open Web Text)

Max Activating Token Index: 242

Text #17

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.6077. Min Act: -0.1700

Data Index: 4083262 (Open Web Text)

Max Activating Token Index: 368

Text #18

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.5858. Min Act: -0.1700

Data Index: 584996 (Open Web Text)

Max Activating Token Index: 452

Text #19

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.5922. Min Act: -0.1700

Data Index: 5151533 (Open Web Text)

Max Activating Token Index: 325