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

Dataset: Open Web Text

Neuron 1300 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: 2.3128. Min Range: -2.3128

Max Act: 2.2978. Min Act: -0.1700

Data Index: 4888082 (Open Web Text)

Max Activating Token Index: 88

Text #1

Max Range: 2.3128. Min Range: -2.3128

Max Act: 2.3061. Min Act: -0.1700

Data Index: 4231795 (Open Web Text)

Max Activating Token Index: 286

Text #2

Max Range: 2.3128. Min Range: -2.3128

Max Act: 2.3128. Min Act: -0.1700

Data Index: 6221249 (Open Web Text)

Max Activating Token Index: 648

Text #3

Max Range: 2.3128. Min Range: -2.3128

Max Act: 2.2878. Min Act: -0.1700

Data Index: 2940228 (Open Web Text)

Max Activating Token Index: 406

Text #4

Max Range: 2.3128. Min Range: -2.3128

Max Act: 2.2867. Min Act: -0.1700

Data Index: 780968 (Open Web Text)

Max Activating Token Index: 729

Text #5

Max Range: 2.3128. Min Range: -2.3128

Max Act: 2.2839. Min Act: -0.1700

Data Index: 5111914 (Open Web Text)

Max Activating Token Index: 928

Text #6

Max Range: 2.3128. Min Range: -2.3128

Max Act: 2.2547. Min Act: -0.1700

Data Index: 7971552 (Open Web Text)

Max Activating Token Index: 364

Text #7

Max Range: 2.3128. Min Range: -2.3128

Max Act: 2.2608. Min Act: -0.1700

Data Index: 7032787 (Open Web Text)

Max Activating Token Index: 181

Text #8

Max Range: 2.3128. Min Range: -2.3128

Max Act: 2.2551. Min Act: -0.1700

Data Index: 2152591 (Open Web Text)

Max Activating Token Index: 264

Text #9

Max Range: 2.3128. Min Range: -2.3128

Max Act: 2.2584. Min Act: -0.1700

Data Index: 6317236 (Open Web Text)

Max Activating Token Index: 649

Text #10

Max Range: 2.3128. Min Range: -2.3128

Max Act: 2.2448. Min Act: -0.1700

Data Index: 5120115 (Open Web Text)

Max Activating Token Index: 912

Text #11

Max Range: 2.3128. Min Range: -2.3128

Max Act: 2.2465. Min Act: -0.1700

Data Index: 5601356 (Open Web Text)

Max Activating Token Index: 562

Text #12

Max Range: 2.3128. Min Range: -2.3128

Max Act: 2.2274. Min Act: -0.1700

Data Index: 881686 (Open Web Text)

Max Activating Token Index: 71

Text #13

Max Range: 2.3128. Min Range: -2.3128

Max Act: 2.2159. Min Act: -0.1700

Data Index: 4479542 (Open Web Text)

Max Activating Token Index: 433

Text #14

Max Range: 2.3128. Min Range: -2.3128

Max Act: 2.2277. Min Act: -0.1700

Data Index: 1539598 (Open Web Text)

Max Activating Token Index: 603

Text #15

Max Range: 2.3128. Min Range: -2.3128

Max Act: 2.2214. Min Act: -0.1700

Data Index: 6373067 (Open Web Text)

Max Activating Token Index: 48

Text #16

Max Range: 2.3128. Min Range: -2.3128

Max Act: 2.2303. Min Act: -0.1700

Data Index: 4396197 (Open Web Text)

Max Activating Token Index: 273

Text #17

Max Range: 2.3128. Min Range: -2.3128

Max Act: 2.2294. Min Act: -0.1700

Data Index: 5918704 (Open Web Text)

Max Activating Token Index: 565

Text #18

Max Range: 2.3128. Min Range: -2.3128

Max Act: 2.2288. Min Act: -0.1700

Data Index: 3898408 (Open Web Text)

Max Activating Token Index: 961

Text #19

Max Range: 2.3128. Min Range: -2.3128

Max Act: 2.2286. Min Act: -0.1700

Data Index: 3414234 (Open Web Text)

Max Activating Token Index: 548