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

Dataset: Open Web Text

Neuron 2170 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: 3.1214. Min Range: -3.1214

Max Act: 3.1214. Min Act: -0.1700

Data Index: 2720453 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.1214. Min Range: -3.1214

Max Act: 3.0410. Min Act: -0.1700

Data Index: 453621 (Open Web Text)

Max Activating Token Index: 683

Text #2

Max Range: 3.1214. Min Range: -3.1214

Max Act: 3.0331. Min Act: -0.1700

Data Index: 5246335 (Open Web Text)

Max Activating Token Index: 112

Text #3

Max Range: 3.1214. Min Range: -3.1214

Max Act: 3.0043. Min Act: -0.1700

Data Index: 7364389 (Open Web Text)

Max Activating Token Index: 218

Text #4

Max Range: 3.1214. Min Range: -3.1214

Max Act: 2.9764. Min Act: -0.1700

Data Index: 4415982 (Open Web Text)

Max Activating Token Index: 956

Text #5

Max Range: 3.1214. Min Range: -3.1214

Max Act: 2.9633. Min Act: -0.1700

Data Index: 6489244 (Open Web Text)

Max Activating Token Index: 221

Text #6

Max Range: 3.1214. Min Range: -3.1214

Max Act: 2.9941. Min Act: -0.1700

Data Index: 7459996 (Open Web Text)

Max Activating Token Index: 574

Text #7

Max Range: 3.1214. Min Range: -3.1214

Max Act: 2.9606. Min Act: -0.1700

Data Index: 4159676 (Open Web Text)

Max Activating Token Index: 821

Text #8

Max Range: 3.1214. Min Range: -3.1214

Max Act: 2.9532. Min Act: -0.1700

Data Index: 6039929 (Open Web Text)

Max Activating Token Index: 738

Text #9

Max Range: 3.1214. Min Range: -3.1214

Max Act: 2.9420. Min Act: -0.1700

Data Index: 4034352 (Open Web Text)

Max Activating Token Index: 499

Text #10

Max Range: 3.1214. Min Range: -3.1214

Max Act: 2.8970. Min Act: -0.1700

Data Index: 7172878 (Open Web Text)

Max Activating Token Index: 113

Text #11

Max Range: 3.1214. Min Range: -3.1214

Max Act: 2.8966. Min Act: -0.1700

Data Index: 3238745 (Open Web Text)

Max Activating Token Index: 124

Text #12

Max Range: 3.1214. Min Range: -3.1214

Max Act: 2.8746. Min Act: -0.1700

Data Index: 2627948 (Open Web Text)

Max Activating Token Index: 328

Text #13

Max Range: 3.1214. Min Range: -3.1214

Max Act: 2.8786. Min Act: -0.1700

Data Index: 587337 (Open Web Text)

Max Activating Token Index: 278

Text #14

Max Range: 3.1214. Min Range: -3.1214

Max Act: 2.8603. Min Act: -0.1700

Data Index: 412464 (Open Web Text)

Max Activating Token Index: 482

Text #15

Max Range: 3.1214. Min Range: -3.1214

Max Act: 2.9030. Min Act: -0.1700

Data Index: 3284433 (Open Web Text)

Max Activating Token Index: 530

Text #16

Max Range: 3.1214. Min Range: -3.1214

Max Act: 2.8952. Min Act: -0.1700

Data Index: 4047849 (Open Web Text)

Max Activating Token Index: 562

Text #17

Max Range: 3.1214. Min Range: -3.1214

Max Act: 2.8824. Min Act: -0.1700

Data Index: 412463 (Open Web Text)

Max Activating Token Index: 971

Text #18

Max Range: 3.1214. Min Range: -3.1214

Max Act: 2.8863. Min Act: -0.1700

Data Index: 995114 (Open Web Text)

Max Activating Token Index: 926

Text #19

Max Range: 3.1214. Min Range: -3.1214

Max Act: 2.8768. Min Act: -0.1700

Data Index: 6298322 (Open Web Text)

Max Activating Token Index: 872