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

Dataset: Open Web Text

Neuron 536 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: 5.0416. Min Range: -5.0416

Max Act: 5.0416. Min Act: -0.1700

Data Index: 3207069 (Open Web Text)

Max Activating Token Index: 639

Text #1

Max Range: 5.0416. Min Range: -5.0416

Max Act: 5.0174. Min Act: -0.1700

Data Index: 5456656 (Open Web Text)

Max Activating Token Index: 754

Text #2

Max Range: 5.0416. Min Range: -5.0416

Max Act: 4.9696. Min Act: -0.1700

Data Index: 1306584 (Open Web Text)

Max Activating Token Index: 206

Text #3

Max Range: 5.0416. Min Range: -5.0416

Max Act: 4.9826. Min Act: -0.1700

Data Index: 3139852 (Open Web Text)

Max Activating Token Index: 407

Text #4

Max Range: 5.0416. Min Range: -5.0416

Max Act: 4.8579. Min Act: -0.1700

Data Index: 7685731 (Open Web Text)

Max Activating Token Index: 313

Text #5

Max Range: 5.0416. Min Range: -5.0416

Max Act: 4.8266. Min Act: -0.1700

Data Index: 2360069 (Open Web Text)

Max Activating Token Index: 220

Text #6

Max Range: 5.0416. Min Range: -5.0416

Max Act: 4.8310. Min Act: -0.1700

Data Index: 6486542 (Open Web Text)

Max Activating Token Index: 996

Text #7

Max Range: 5.0416. Min Range: -5.0416

Max Act: 4.7649. Min Act: -0.1700

Data Index: 7882363 (Open Web Text)

Max Activating Token Index: 987

Text #8

Max Range: 5.0416. Min Range: -5.0416

Max Act: 4.7903. Min Act: -0.1700

Data Index: 693683 (Open Web Text)

Max Activating Token Index: 422

Text #9

Max Range: 5.0416. Min Range: -5.0416

Max Act: 4.7953. Min Act: -0.1700

Data Index: 8484765 (Open Web Text)

Max Activating Token Index: 451

Text #10

Max Range: 5.0416. Min Range: -5.0416

Max Act: 4.7989. Min Act: -0.1700

Data Index: 1944676 (Open Web Text)

Max Activating Token Index: 556

Text #11

Max Range: 5.0416. Min Range: -5.0416

Max Act: 4.7433. Min Act: -0.1700

Data Index: 8481774 (Open Web Text)

Max Activating Token Index: 738

Text #12

Max Range: 5.0416. Min Range: -5.0416

Max Act: 4.7540. Min Act: -0.1700

Data Index: 5098250 (Open Web Text)

Max Activating Token Index: 500

Text #13

Max Range: 5.0416. Min Range: -5.0416

Max Act: 4.7244. Min Act: -0.1700

Data Index: 1207554 (Open Web Text)

Max Activating Token Index: 808

Text #14

Max Range: 5.0416. Min Range: -5.0416

Max Act: 4.7117. Min Act: -0.1700

Data Index: 5777672 (Open Web Text)

Max Activating Token Index: 335

Text #15

Max Range: 5.0416. Min Range: -5.0416

Max Act: 4.7519. Min Act: -0.1700

Data Index: 3305236 (Open Web Text)

Max Activating Token Index: 537

Text #16

Max Range: 5.0416. Min Range: -5.0416

Max Act: 4.7290. Min Act: -0.1700

Data Index: 3907074 (Open Web Text)

Max Activating Token Index: 309

Text #17

Max Range: 5.0416. Min Range: -5.0416

Max Act: 4.6963. Min Act: -0.1700

Data Index: 7434612 (Open Web Text)

Max Activating Token Index: 763

Text #18

Max Range: 5.0416. Min Range: -5.0416

Max Act: 4.6913. Min Act: -0.1700

Data Index: 7298753 (Open Web Text)

Max Activating Token Index: 549

Text #19

Max Range: 5.0416. Min Range: -5.0416

Max Act: 4.7053. Min Act: -0.1700

Data Index: 4950219 (Open Web Text)

Max Activating Token Index: 203