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

Dataset: Open Web Text

Neuron 1593 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: 3.8189. Min Range: -3.8189

Max Act: 3.8189. Min Act: -0.1700

Data Index: 942097 (Open Web Text)

Max Activating Token Index: 312

Text #1

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.7588. Min Act: -0.1700

Data Index: 1492264 (Open Web Text)

Max Activating Token Index: 549

Text #2

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.7227. Min Act: -0.1700

Data Index: 1797067 (Open Web Text)

Max Activating Token Index: 234

Text #3

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.7322. Min Act: -0.1700

Data Index: 1076764 (Open Web Text)

Max Activating Token Index: 424

Text #4

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.7777. Min Act: -0.1700

Data Index: 3458630 (Open Web Text)

Max Activating Token Index: 856

Text #5

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.7524. Min Act: -0.1700

Data Index: 25272 (Open Web Text)

Max Activating Token Index: 18

Text #6

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.7218. Min Act: -0.1700

Data Index: 7996810 (Open Web Text)

Max Activating Token Index: 288

Text #7

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.6905. Min Act: -0.1700

Data Index: 6383363 (Open Web Text)

Max Activating Token Index: 505

Text #8

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.6910. Min Act: -0.1700

Data Index: 5839574 (Open Web Text)

Max Activating Token Index: 312

Text #9

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.7095. Min Act: -0.1700

Data Index: 3372171 (Open Web Text)

Max Activating Token Index: 146

Text #10

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.6860. Min Act: -0.1700

Data Index: 7403433 (Open Web Text)

Max Activating Token Index: 366

Text #11

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.6685. Min Act: -0.1700

Data Index: 8593692 (Open Web Text)

Max Activating Token Index: 738

Text #12

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.6710. Min Act: -0.1700

Data Index: 5811138 (Open Web Text)

Max Activating Token Index: 172

Text #13

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.6596. Min Act: -0.1700

Data Index: 1915231 (Open Web Text)

Max Activating Token Index: 880

Text #14

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.6317. Min Act: -0.1700

Data Index: 2324307 (Open Web Text)

Max Activating Token Index: 488

Text #15

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.6104. Min Act: -0.1700

Data Index: 1856939 (Open Web Text)

Max Activating Token Index: 217

Text #16

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.6383. Min Act: -0.1700

Data Index: 5880095 (Open Web Text)

Max Activating Token Index: 153

Text #17

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.5948. Min Act: -0.1700

Data Index: 7003581 (Open Web Text)

Max Activating Token Index: 201

Text #18

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.5836. Min Act: -0.1700

Data Index: 3306373 (Open Web Text)

Max Activating Token Index: 318

Text #19

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.5929. Min Act: -0.1700

Data Index: 311711 (Open Web Text)

Max Activating Token Index: 245