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

Dataset: Open Web Text

Neuron 2416 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: 3.9304. Min Range: -3.9304

Max Act: 3.9304. Min Act: -0.1700

Data Index: 1723741 (Open Web Text)

Max Activating Token Index: 433

Text #1

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.9029. Min Act: -0.1700

Data Index: 8440439 (Open Web Text)

Max Activating Token Index: 260

Text #2

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.9023. Min Act: -0.1700

Data Index: 3745556 (Open Web Text)

Max Activating Token Index: 199

Text #3

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.9033. Min Act: -0.1700

Data Index: 2294527 (Open Web Text)

Max Activating Token Index: 452

Text #4

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.8708. Min Act: -0.1700

Data Index: 7256184 (Open Web Text)

Max Activating Token Index: 806

Text #5

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.8860. Min Act: -0.1700

Data Index: 6599103 (Open Web Text)

Max Activating Token Index: 736

Text #6

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.8846. Min Act: -0.1700

Data Index: 3580323 (Open Web Text)

Max Activating Token Index: 259

Text #7

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.8555. Min Act: -0.1700

Data Index: 2579324 (Open Web Text)

Max Activating Token Index: 521

Text #8

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.8655. Min Act: -0.1700

Data Index: 8539941 (Open Web Text)

Max Activating Token Index: 191

Text #9

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.8416. Min Act: -0.1700

Data Index: 4759356 (Open Web Text)

Max Activating Token Index: 16

Text #10

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.8528. Min Act: -0.1700

Data Index: 506641 (Open Web Text)

Max Activating Token Index: 32

Text #11

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.8670. Min Act: -0.1700

Data Index: 329220 (Open Web Text)

Max Activating Token Index: 173

Text #12

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.8435. Min Act: -0.1700

Data Index: 8639593 (Open Web Text)

Max Activating Token Index: 887

Text #13

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.8057. Min Act: -0.1700

Data Index: 3621715 (Open Web Text)

Max Activating Token Index: 336

Text #14

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.8208. Min Act: -0.1700

Data Index: 4988795 (Open Web Text)

Max Activating Token Index: 916

Text #15

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.8290. Min Act: -0.1700

Data Index: 5809029 (Open Web Text)

Max Activating Token Index: 242

Text #16

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.7940. Min Act: -0.1700

Data Index: 4870139 (Open Web Text)

Max Activating Token Index: 297

Text #17

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.8101. Min Act: -0.1700

Data Index: 1356870 (Open Web Text)

Max Activating Token Index: 539

Text #18

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.8130. Min Act: -0.1700

Data Index: 2824805 (Open Web Text)

Max Activating Token Index: 400

Text #19

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.8215. Min Act: -0.1700

Data Index: 4777586 (Open Web Text)

Max Activating Token Index: 217