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

Dataset: Open Web Text

Neuron 291 in Layer 6

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: 4.0099. Min Range: -4.0099

Max Act: 4.0099. Min Act: -0.1700

Data Index: 974485 (Open Web Text)

Max Activating Token Index: 867

Text #1

Max Range: 4.0099. Min Range: -4.0099

Max Act: 3.9164. Min Act: -0.1700

Data Index: 5546422 (Open Web Text)

Max Activating Token Index: 892

Text #2

Max Range: 4.0099. Min Range: -4.0099

Max Act: 3.9449. Min Act: -0.1700

Data Index: 7289945 (Open Web Text)

Max Activating Token Index: 159

Text #3

Max Range: 4.0099. Min Range: -4.0099

Max Act: 3.9338. Min Act: -0.1700

Data Index: 4244688 (Open Web Text)

Max Activating Token Index: 638

Text #4

Max Range: 4.0099. Min Range: -4.0099

Max Act: 3.9056. Min Act: -0.1700

Data Index: 68556 (Open Web Text)

Max Activating Token Index: 789

Text #5

Max Range: 4.0099. Min Range: -4.0099

Max Act: 3.9170. Min Act: -0.1700

Data Index: 2809433 (Open Web Text)

Max Activating Token Index: 846

Text #6

Max Range: 4.0099. Min Range: -4.0099

Max Act: 3.8580. Min Act: -0.1700

Data Index: 7181123 (Open Web Text)

Max Activating Token Index: 828

Text #7

Max Range: 4.0099. Min Range: -4.0099

Max Act: 3.8673. Min Act: -0.1700

Data Index: 5305241 (Open Web Text)

Max Activating Token Index: 950

Text #8

Max Range: 4.0099. Min Range: -4.0099

Max Act: 3.8426. Min Act: -0.1700

Data Index: 3714402 (Open Web Text)

Max Activating Token Index: 265

Text #9

Max Range: 4.0099. Min Range: -4.0099

Max Act: 3.8127. Min Act: -0.1700

Data Index: 5627260 (Open Web Text)

Max Activating Token Index: 52

Text #10

Max Range: 4.0099. Min Range: -4.0099

Max Act: 3.8236. Min Act: -0.1700

Data Index: 6137067 (Open Web Text)

Max Activating Token Index: 752

Text #11

Max Range: 4.0099. Min Range: -4.0099

Max Act: 3.8104. Min Act: -0.1700

Data Index: 2784684 (Open Web Text)

Max Activating Token Index: 950

Text #12

Max Range: 4.0099. Min Range: -4.0099

Max Act: 3.8179. Min Act: -0.1700

Data Index: 5960287 (Open Web Text)

Max Activating Token Index: 500

Text #13

Max Range: 4.0099. Min Range: -4.0099

Max Act: 3.7733. Min Act: -0.1700

Data Index: 1476413 (Open Web Text)

Max Activating Token Index: 186

Text #14

Max Range: 4.0099. Min Range: -4.0099

Max Act: 3.7998. Min Act: -0.1700

Data Index: 3190480 (Open Web Text)

Max Activating Token Index: 586

Text #15

Max Range: 4.0099. Min Range: -4.0099

Max Act: 3.7583. Min Act: -0.1700

Data Index: 6547086 (Open Web Text)

Max Activating Token Index: 269

Text #16

Max Range: 4.0099. Min Range: -4.0099

Max Act: 3.7823. Min Act: -0.1700

Data Index: 457804 (Open Web Text)

Max Activating Token Index: 409

Text #17

Max Range: 4.0099. Min Range: -4.0099

Max Act: 3.7821. Min Act: -0.1700

Data Index: 779838 (Open Web Text)

Max Activating Token Index: 245

Text #18

Max Range: 4.0099. Min Range: -4.0099

Max Act: 3.7600. Min Act: -0.1700

Data Index: 1694287 (Open Web Text)

Max Activating Token Index: 298

Text #19

Max Range: 4.0099. Min Range: -4.0099

Max Act: 3.7604. Min Act: -0.1700

Data Index: 8306050 (Open Web Text)

Max Activating Token Index: 837