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

Dataset: Open Web Text

Neuron 2880 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: 4.2478. Min Range: -4.2478

Max Act: 4.2478. Min Act: -0.1700

Data Index: 4865802 (Open Web Text)

Max Activating Token Index: 339

Text #1

Max Range: 4.2478. Min Range: -4.2478

Max Act: 4.0478. Min Act: -0.1700

Data Index: 682061 (Open Web Text)

Max Activating Token Index: 334

Text #2

Max Range: 4.2478. Min Range: -4.2478

Max Act: 4.0170. Min Act: -0.1700

Data Index: 4925650 (Open Web Text)

Max Activating Token Index: 409

Text #3

Max Range: 4.2478. Min Range: -4.2478

Max Act: 4.0086. Min Act: -0.1700

Data Index: 3887176 (Open Web Text)

Max Activating Token Index: 410

Text #4

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.9909. Min Act: -0.1700

Data Index: 1593376 (Open Web Text)

Max Activating Token Index: 458

Text #5

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.9421. Min Act: -0.1700

Data Index: 7574945 (Open Web Text)

Max Activating Token Index: 127

Text #6

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.9602. Min Act: -0.1700

Data Index: 4919066 (Open Web Text)

Max Activating Token Index: 29

Text #7

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.9329. Min Act: -0.1700

Data Index: 3823136 (Open Web Text)

Max Activating Token Index: 28

Text #8

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.9248. Min Act: -0.1700

Data Index: 3193303 (Open Web Text)

Max Activating Token Index: 192

Text #9

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.9260. Min Act: -0.1700

Data Index: 6486090 (Open Web Text)

Max Activating Token Index: 658

Text #10

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.9532. Min Act: -0.1700

Data Index: 5728092 (Open Web Text)

Max Activating Token Index: 303

Text #11

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.9444. Min Act: -0.1700

Data Index: 6183857 (Open Web Text)

Max Activating Token Index: 879

Text #12

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.9072. Min Act: -0.1700

Data Index: 5462774 (Open Web Text)

Max Activating Token Index: 700

Text #13

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.8936. Min Act: -0.1700

Data Index: 2004395 (Open Web Text)

Max Activating Token Index: 330

Text #14

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.8833. Min Act: -0.1700

Data Index: 157654 (Open Web Text)

Max Activating Token Index: 735

Text #15

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.8896. Min Act: -0.1700

Data Index: 3324151 (Open Web Text)

Max Activating Token Index: 642

Text #16

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.8661. Min Act: -0.1700

Data Index: 5265056 (Open Web Text)

Max Activating Token Index: 523

Text #17

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.8819. Min Act: -0.1700

Data Index: 2125170 (Open Web Text)

Max Activating Token Index: 536

Text #18

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.8750. Min Act: -0.1700

Data Index: 6719781 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.8818. Min Act: -0.1700

Data Index: 2721290 (Open Web Text)

Max Activating Token Index: 538