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

Dataset: Open Web Text

Neuron 3031 in Layer 2

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: 4.6994. Min Range: -4.6994

Max Act: 4.6994. Min Act: -0.1700

Data Index: 4830919 (Open Web Text)

Max Activating Token Index: 391

Text #1

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.6444. Min Act: -0.1700

Data Index: 991503 (Open Web Text)

Max Activating Token Index: 337

Text #2

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.6060. Min Act: -0.1700

Data Index: 7249343 (Open Web Text)

Max Activating Token Index: 690

Text #3

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.5757. Min Act: -0.1700

Data Index: 8464302 (Open Web Text)

Max Activating Token Index: 267

Text #4

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.5643. Min Act: -0.1700

Data Index: 8269974 (Open Web Text)

Max Activating Token Index: 871

Text #5

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.5218. Min Act: -0.1700

Data Index: 4860642 (Open Web Text)

Max Activating Token Index: 33

Text #6

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.4874. Min Act: -0.1700

Data Index: 2926953 (Open Web Text)

Max Activating Token Index: 777

Text #7

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.5200. Min Act: -0.1700

Data Index: 7420178 (Open Web Text)

Max Activating Token Index: 488

Text #8

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.5093. Min Act: -0.1700

Data Index: 5738638 (Open Web Text)

Max Activating Token Index: 729

Text #9

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.4549. Min Act: -0.1700

Data Index: 2086878 (Open Web Text)

Max Activating Token Index: 853

Text #10

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.4515. Min Act: -0.1700

Data Index: 1200833 (Open Web Text)

Max Activating Token Index: 513

Text #11

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.4784. Min Act: -0.1700

Data Index: 883923 (Open Web Text)

Max Activating Token Index: 395

Text #12

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.4865. Min Act: -0.1700

Data Index: 2689798 (Open Web Text)

Max Activating Token Index: 408

Text #13

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.4430. Min Act: -0.1700

Data Index: 3104575 (Open Web Text)

Max Activating Token Index: 674

Text #14

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.4663. Min Act: -0.1700

Data Index: 461314 (Open Web Text)

Max Activating Token Index: 766

Text #15

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.4506. Min Act: -0.1700

Data Index: 3412119 (Open Web Text)

Max Activating Token Index: 307

Text #16

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.4906. Min Act: -0.1700

Data Index: 3368393 (Open Web Text)

Max Activating Token Index: 601

Text #17

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.4635. Min Act: -0.1700

Data Index: 5075808 (Open Web Text)

Max Activating Token Index: 1003

Text #18

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.4642. Min Act: -0.1700

Data Index: 3616157 (Open Web Text)

Max Activating Token Index: 445

Text #19

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.4215. Min Act: -0.1700

Data Index: 3967996 (Open Web Text)

Max Activating Token Index: 461