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

Dataset: Open Web Text

Neuron 3032 in Layer 5

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: 4.8291. Min Range: -4.8291

Max Act: 4.8291. Min Act: -0.1700

Data Index: 7686548 (Open Web Text)

Max Activating Token Index: 436

Text #1

Max Range: 4.8291. Min Range: -4.8291

Max Act: 4.8003. Min Act: -0.1700

Data Index: 7686535 (Open Web Text)

Max Activating Token Index: 871

Text #2

Max Range: 4.8291. Min Range: -4.8291

Max Act: 4.7888. Min Act: -0.1700

Data Index: 6490116 (Open Web Text)

Max Activating Token Index: 791

Text #3

Max Range: 4.8291. Min Range: -4.8291

Max Act: 4.6983. Min Act: -0.1700

Data Index: 6749262 (Open Web Text)

Max Activating Token Index: 215

Text #4

Max Range: 4.8291. Min Range: -4.8291

Max Act: 4.7354. Min Act: -0.1700

Data Index: 2279695 (Open Web Text)

Max Activating Token Index: 929

Text #5

Max Range: 4.8291. Min Range: -4.8291

Max Act: 4.6691. Min Act: -0.1700

Data Index: 7495848 (Open Web Text)

Max Activating Token Index: 401

Text #6

Max Range: 4.8291. Min Range: -4.8291

Max Act: 4.6153. Min Act: -0.1700

Data Index: 3927444 (Open Web Text)

Max Activating Token Index: 232

Text #7

Max Range: 4.8291. Min Range: -4.8291

Max Act: 4.5945. Min Act: -0.1700

Data Index: 7686536 (Open Web Text)

Max Activating Token Index: 128

Text #8

Max Range: 4.8291. Min Range: -4.8291

Max Act: 4.5698. Min Act: -0.1700

Data Index: 6583492 (Open Web Text)

Max Activating Token Index: 216

Text #9

Max Range: 4.8291. Min Range: -4.8291

Max Act: 4.5571. Min Act: -0.1700

Data Index: 6553636 (Open Web Text)

Max Activating Token Index: 794

Text #10

Max Range: 4.8291. Min Range: -4.8291

Max Act: 4.5334. Min Act: -0.1700

Data Index: 5675591 (Open Web Text)

Max Activating Token Index: 908

Text #11

Max Range: 4.8291. Min Range: -4.8291

Max Act: 4.5408. Min Act: -0.1700

Data Index: 5484638 (Open Web Text)

Max Activating Token Index: 899

Text #12

Max Range: 4.8291. Min Range: -4.8291

Max Act: 4.5579. Min Act: -0.1700

Data Index: 5153621 (Open Web Text)

Max Activating Token Index: 937

Text #13

Max Range: 4.8291. Min Range: -4.8291

Max Act: 4.5161. Min Act: -0.1700

Data Index: 3938104 (Open Web Text)

Max Activating Token Index: 873

Text #14

Max Range: 4.8291. Min Range: -4.8291

Max Act: 4.4984. Min Act: -0.1700

Data Index: 331539 (Open Web Text)

Max Activating Token Index: 451

Text #15

Max Range: 4.8291. Min Range: -4.8291

Max Act: 4.5363. Min Act: -0.1700

Data Index: 111251 (Open Web Text)

Max Activating Token Index: 558

Text #16

Max Range: 4.8291. Min Range: -4.8291

Max Act: 4.5191. Min Act: -0.1700

Data Index: 7580536 (Open Web Text)

Max Activating Token Index: 12

Text #17

Max Range: 4.8291. Min Range: -4.8291

Max Act: 4.5110. Min Act: -0.1700

Data Index: 3789100 (Open Web Text)

Max Activating Token Index: 811

Text #18

Max Range: 4.8291. Min Range: -4.8291

Max Act: 4.5223. Min Act: -0.1700

Data Index: 5787639 (Open Web Text)

Max Activating Token Index: 834

Text #19

Max Range: 4.8291. Min Range: -4.8291

Max Act: 4.5192. Min Act: -0.1700

Data Index: 7125910 (Open Web Text)

Max Activating Token Index: 895