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

Dataset: Open Web Text

Neuron 2455 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: 4.0002. Min Range: -4.0002

Max Act: 4.0002. Min Act: -0.1700

Data Index: 6180064 (Open Web Text)

Max Activating Token Index: 625

Text #1

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.8409. Min Act: -0.1700

Data Index: 3569003 (Open Web Text)

Max Activating Token Index: 35

Text #2

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.8204. Min Act: -0.1700

Data Index: 3366508 (Open Web Text)

Max Activating Token Index: 498

Text #3

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.7914. Min Act: -0.1700

Data Index: 4176654 (Open Web Text)

Max Activating Token Index: 427

Text #4

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.7910. Min Act: -0.1700

Data Index: 5657647 (Open Web Text)

Max Activating Token Index: 878

Text #5

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.7857. Min Act: -0.1700

Data Index: 722415 (Open Web Text)

Max Activating Token Index: 618

Text #6

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.7864. Min Act: -0.1700

Data Index: 6860622 (Open Web Text)

Max Activating Token Index: 555

Text #7

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.7454. Min Act: -0.1700

Data Index: 2995375 (Open Web Text)

Max Activating Token Index: 539

Text #8

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.7663. Min Act: -0.1700

Data Index: 6068768 (Open Web Text)

Max Activating Token Index: 122

Text #9

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.7537. Min Act: -0.1700

Data Index: 722416 (Open Web Text)

Max Activating Token Index: 332

Text #10

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.7855. Min Act: -0.1700

Data Index: 5339051 (Open Web Text)

Max Activating Token Index: 471

Text #11

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.7987. Min Act: -0.1700

Data Index: 5166275 (Open Web Text)

Max Activating Token Index: 27

Text #12

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.7680. Min Act: -0.1700

Data Index: 7535476 (Open Web Text)

Max Activating Token Index: 618

Text #13

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.7658. Min Act: -0.1700

Data Index: 2653751 (Open Web Text)

Max Activating Token Index: 831

Text #14

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.7350. Min Act: -0.1700

Data Index: 1944303 (Open Web Text)

Max Activating Token Index: 716

Text #15

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.7655. Min Act: -0.1700

Data Index: 1194357 (Open Web Text)

Max Activating Token Index: 640

Text #16

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.6939. Min Act: -0.1700

Data Index: 3622987 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.7198. Min Act: -0.1700

Data Index: 558457 (Open Web Text)

Max Activating Token Index: 379

Text #18

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.6930. Min Act: -0.1700

Data Index: 955304 (Open Web Text)

Max Activating Token Index: 498

Text #19

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.6993. Min Act: -0.1700

Data Index: 6679117 (Open Web Text)

Max Activating Token Index: 231