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

Dataset: Open Web Text

Neuron 41 in Layer 0

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: 4.1887. Min Range: -4.1887

Max Act: 4.1887. Min Act: -0.1700

Data Index: 7487096 (Open Web Text)

Max Activating Token Index: 480

Text #1

Max Range: 4.1887. Min Range: -4.1887

Max Act: 4.0560. Min Act: -0.1700

Data Index: 7487095 (Open Web Text)

Max Activating Token Index: 401

Text #2

Max Range: 4.1887. Min Range: -4.1887

Max Act: 3.8133. Min Act: -0.1700

Data Index: 7487097 (Open Web Text)

Max Activating Token Index: 84

Text #3

Max Range: 4.1887. Min Range: -4.1887

Max Act: 3.7307. Min Act: -0.1700

Data Index: 7487098 (Open Web Text)

Max Activating Token Index: 985

Text #4

Max Range: 4.1887. Min Range: -4.1887

Max Act: 3.6604. Min Act: -0.1700

Data Index: 7352925 (Open Web Text)

Max Activating Token Index: 959

Text #5

Max Range: 4.1887. Min Range: -4.1887

Max Act: 3.6040. Min Act: -0.1700

Data Index: 3062910 (Open Web Text)

Max Activating Token Index: 534

Text #6

Max Range: 4.1887. Min Range: -4.1887

Max Act: 3.5947. Min Act: -0.1700

Data Index: 2783616 (Open Web Text)

Max Activating Token Index: 768

Text #7

Max Range: 4.1887. Min Range: -4.1887

Max Act: 3.5689. Min Act: -0.1700

Data Index: 3062908 (Open Web Text)

Max Activating Token Index: 949

Text #8

Max Range: 4.1887. Min Range: -4.1887

Max Act: 3.5602. Min Act: -0.1700

Data Index: 6469838 (Open Web Text)

Max Activating Token Index: 835

Text #9

Max Range: 4.1887. Min Range: -4.1887

Max Act: 3.5603. Min Act: -0.1699

Data Index: 3062909 (Open Web Text)

Max Activating Token Index: 576

Text #10

Max Range: 4.1887. Min Range: -4.1887

Max Act: 3.5342. Min Act: -0.1700

Data Index: 2783617 (Open Web Text)

Max Activating Token Index: 265

Text #11

Max Range: 4.1887. Min Range: -4.1887

Max Act: 3.5329. Min Act: -0.1700

Data Index: 1341896 (Open Web Text)

Max Activating Token Index: 410

Text #12

Max Range: 4.1887. Min Range: -4.1887

Max Act: 3.4794. Min Act: -0.1700

Data Index: 5531908 (Open Web Text)

Max Activating Token Index: 507

Text #13

Max Range: 4.1887. Min Range: -4.1887

Max Act: 3.4728. Min Act: -0.1700

Data Index: 2783618 (Open Web Text)

Max Activating Token Index: 181

Text #14

Max Range: 4.1887. Min Range: -4.1887

Max Act: 3.4282. Min Act: -0.1700

Data Index: 4763949 (Open Web Text)

Max Activating Token Index: 358

Text #15

Max Range: 4.1887. Min Range: -4.1887

Max Act: 3.4271. Min Act: -0.1700

Data Index: 4763962 (Open Web Text)

Max Activating Token Index: 343

Text #16

Max Range: 4.1887. Min Range: -4.1887

Max Act: 3.4110. Min Act: -0.1700

Data Index: 5082616 (Open Web Text)

Max Activating Token Index: 530

Text #17

Max Range: 4.1887. Min Range: -4.1887

Max Act: 3.4071. Min Act: -0.1700

Data Index: 4399391 (Open Web Text)

Max Activating Token Index: 394

Text #18

Max Range: 4.1887. Min Range: -4.1887

Max Act: 3.4046. Min Act: -0.1700

Data Index: 8274165 (Open Web Text)

Max Activating Token Index: 918

Text #19

Max Range: 4.1887. Min Range: -4.1887

Max Act: 3.4023. Min Act: -0.1700

Data Index: 3394859 (Open Web Text)

Max Activating Token Index: 383