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

Dataset: Open Web Text

Neuron 2376 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: 3.7580. Min Range: -3.7580

Max Act: 3.7069. Min Act: -0.1700

Data Index: 3303696 (Open Web Text)

Max Activating Token Index: 224

Text #1

Max Range: 3.7580. Min Range: -3.7580

Max Act: 3.7580. Min Act: -0.1700

Data Index: 982519 (Open Web Text)

Max Activating Token Index: 470

Text #2

Max Range: 3.7580. Min Range: -3.7580

Max Act: 3.6720. Min Act: -0.1700

Data Index: 3508770 (Open Web Text)

Max Activating Token Index: 815

Text #3

Max Range: 3.7580. Min Range: -3.7580

Max Act: 3.7011. Min Act: -0.1700

Data Index: 8663385 (Open Web Text)

Max Activating Token Index: 515

Text #4

Max Range: 3.7580. Min Range: -3.7580

Max Act: 3.6540. Min Act: -0.1700

Data Index: 1031071 (Open Web Text)

Max Activating Token Index: 275

Text #5

Max Range: 3.7580. Min Range: -3.7580

Max Act: 3.6225. Min Act: -0.1700

Data Index: 8450024 (Open Web Text)

Max Activating Token Index: 550

Text #6

Max Range: 3.7580. Min Range: -3.7580

Max Act: 3.5607. Min Act: -0.1700

Data Index: 1765055 (Open Web Text)

Max Activating Token Index: 563

Text #7

Max Range: 3.7580. Min Range: -3.7580

Max Act: 3.5339. Min Act: -0.1700

Data Index: 1582201 (Open Web Text)

Max Activating Token Index: 980

Text #8

Max Range: 3.7580. Min Range: -3.7580

Max Act: 3.5250. Min Act: -0.1700

Data Index: 3753437 (Open Web Text)

Max Activating Token Index: 283

Text #9

Max Range: 3.7580. Min Range: -3.7580

Max Act: 3.5166. Min Act: -0.1700

Data Index: 2106745 (Open Web Text)

Max Activating Token Index: 256

Text #10

Max Range: 3.7580. Min Range: -3.7580

Max Act: 3.4858. Min Act: -0.1700

Data Index: 7570653 (Open Web Text)

Max Activating Token Index: 466

Text #11

Max Range: 3.7580. Min Range: -3.7580

Max Act: 3.5097. Min Act: -0.1700

Data Index: 5074799 (Open Web Text)

Max Activating Token Index: 539

Text #12

Max Range: 3.7580. Min Range: -3.7580

Max Act: 3.5194. Min Act: -0.1700

Data Index: 3200265 (Open Web Text)

Max Activating Token Index: 738

Text #13

Max Range: 3.7580. Min Range: -3.7580

Max Act: 3.5219. Min Act: -0.1700

Data Index: 4789294 (Open Web Text)

Max Activating Token Index: 462

Text #14

Max Range: 3.7580. Min Range: -3.7580

Max Act: 3.5169. Min Act: -0.1700

Data Index: 3103012 (Open Web Text)

Max Activating Token Index: 231

Text #15

Max Range: 3.7580. Min Range: -3.7580

Max Act: 3.5312. Min Act: -0.1700

Data Index: 830825 (Open Web Text)

Max Activating Token Index: 107

Text #16

Max Range: 3.7580. Min Range: -3.7580

Max Act: 3.5342. Min Act: -0.1700

Data Index: 2752935 (Open Web Text)

Max Activating Token Index: 707

Text #17

Max Range: 3.7580. Min Range: -3.7580

Max Act: 3.5431. Min Act: -0.1700

Data Index: 6252271 (Open Web Text)

Max Activating Token Index: 633

Text #18

Max Range: 3.7580. Min Range: -3.7580

Max Act: 3.4891. Min Act: -0.1700

Data Index: 8236496 (Open Web Text)

Max Activating Token Index: 368

Text #19

Max Range: 3.7580. Min Range: -3.7580

Max Act: 3.4708. Min Act: -0.1700

Data Index: 3008841 (Open Web Text)

Max Activating Token Index: 369