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

Dataset: Open Web Text

Neuron 1024 in Layer 3

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: 3.5500. Min Range: -3.5500

Max Act: 3.5500. Min Act: -0.1700

Data Index: 4562111 (Open Web Text)

Max Activating Token Index: 852

Text #1

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.4155. Min Act: -0.1700

Data Index: 2612949 (Open Web Text)

Max Activating Token Index: 277

Text #2

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.3929. Min Act: -0.1700

Data Index: 425024 (Open Web Text)

Max Activating Token Index: 594

Text #3

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.3807. Min Act: -0.1700

Data Index: 4514493 (Open Web Text)

Max Activating Token Index: 194

Text #4

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.3924. Min Act: -0.1700

Data Index: 3110353 (Open Web Text)

Max Activating Token Index: 334

Text #5

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.3562. Min Act: -0.1700

Data Index: 7493085 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.3602. Min Act: -0.1700

Data Index: 2812764 (Open Web Text)

Max Activating Token Index: 188

Text #7

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.3756. Min Act: -0.1700

Data Index: 1108963 (Open Web Text)

Max Activating Token Index: 491

Text #8

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.3658. Min Act: -0.1700

Data Index: 2066440 (Open Web Text)

Max Activating Token Index: 193

Text #9

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.3457. Min Act: -0.1700

Data Index: 3170783 (Open Web Text)

Max Activating Token Index: 532

Text #10

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.3504. Min Act: -0.1700

Data Index: 8157749 (Open Web Text)

Max Activating Token Index: 143

Text #11

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.3565. Min Act: -0.1700

Data Index: 6393933 (Open Web Text)

Max Activating Token Index: 45

Text #12

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.3375. Min Act: -0.1700

Data Index: 6053198 (Open Web Text)

Max Activating Token Index: 227

Text #13

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.3416. Min Act: -0.1700

Data Index: 6133937 (Open Web Text)

Max Activating Token Index: 630

Text #14

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.3395. Min Act: -0.1700

Data Index: 2451366 (Open Web Text)

Max Activating Token Index: 604

Text #15

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.3417. Min Act: -0.1700

Data Index: 7994976 (Open Web Text)

Max Activating Token Index: 839

Text #16

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.3285. Min Act: -0.1700

Data Index: 3692365 (Open Web Text)

Max Activating Token Index: 288

Text #17

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.3441. Min Act: -0.1700

Data Index: 7479740 (Open Web Text)

Max Activating Token Index: 457

Text #18

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.3234. Min Act: -0.1700

Data Index: 6823491 (Open Web Text)

Max Activating Token Index: 370

Text #19

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.3322. Min Act: -0.1700

Data Index: 2154726 (Open Web Text)

Max Activating Token Index: 228