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

Dataset: Open Web Text

Neuron 1482 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: 4.6874. Min Range: -4.6874

Max Act: 4.6838. Min Act: -0.1700

Data Index: 466465 (Open Web Text)

Max Activating Token Index: 199

Text #1

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.6874. Min Act: -0.1700

Data Index: 1079632 (Open Web Text)

Max Activating Token Index: 485

Text #2

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.6421. Min Act: -0.1700

Data Index: 4995500 (Open Web Text)

Max Activating Token Index: 775

Text #3

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.6205. Min Act: -0.1700

Data Index: 3792621 (Open Web Text)

Max Activating Token Index: 271

Text #4

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.5725. Min Act: -0.1700

Data Index: 6102543 (Open Web Text)

Max Activating Token Index: 876

Text #5

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.5082. Min Act: -0.1700

Data Index: 5521939 (Open Web Text)

Max Activating Token Index: 278

Text #6

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.5069. Min Act: -0.1700

Data Index: 2565407 (Open Web Text)

Max Activating Token Index: 475

Text #7

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.5517. Min Act: -0.1700

Data Index: 789639 (Open Web Text)

Max Activating Token Index: 474

Text #8

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.5297. Min Act: -0.1700

Data Index: 6008706 (Open Web Text)

Max Activating Token Index: 290

Text #9

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.4892. Min Act: -0.1700

Data Index: 5521449 (Open Web Text)

Max Activating Token Index: 744

Text #10

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.4877. Min Act: -0.1700

Data Index: 147687 (Open Web Text)

Max Activating Token Index: 485

Text #11

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.5264. Min Act: -0.1700

Data Index: 8748278 (Open Web Text)

Max Activating Token Index: 48

Text #12

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.5135. Min Act: -0.1700

Data Index: 5470224 (Open Web Text)

Max Activating Token Index: 72

Text #13

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.4906. Min Act: -0.1700

Data Index: 7056266 (Open Web Text)

Max Activating Token Index: 157

Text #14

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.5965. Min Act: -0.1700

Data Index: 6817839 (Open Web Text)

Max Activating Token Index: 948

Text #15

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.5546. Min Act: -0.1700

Data Index: 6416831 (Open Web Text)

Max Activating Token Index: 968

Text #16

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.5090. Min Act: -0.1700

Data Index: 6292188 (Open Web Text)

Max Activating Token Index: 115

Text #17

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.5083. Min Act: -0.1700

Data Index: 2869705 (Open Web Text)

Max Activating Token Index: 939

Text #18

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.4986. Min Act: -0.1700

Data Index: 716432 (Open Web Text)

Max Activating Token Index: 37

Text #19

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.4600. Min Act: -0.1700

Data Index: 2304792 (Open Web Text)

Max Activating Token Index: 234