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

Dataset: Open Web Text

Neuron 256 in Layer 4

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: 5.1581. Min Range: -5.1581

Max Act: 5.1581. Min Act: -0.1700

Data Index: 7544576 (Open Web Text)

Max Activating Token Index: 870

Text #1

Max Range: 5.1581. Min Range: -5.1581

Max Act: 5.0890. Min Act: -0.1700

Data Index: 2612604 (Open Web Text)

Max Activating Token Index: 317

Text #2

Max Range: 5.1581. Min Range: -5.1581

Max Act: 5.0954. Min Act: -0.1700

Data Index: 3271970 (Open Web Text)

Max Activating Token Index: 553

Text #3

Max Range: 5.1581. Min Range: -5.1581

Max Act: 5.0901. Min Act: -0.1700

Data Index: 4884413 (Open Web Text)

Max Activating Token Index: 145

Text #4

Max Range: 5.1581. Min Range: -5.1581

Max Act: 5.0772. Min Act: -0.1700

Data Index: 6642567 (Open Web Text)

Max Activating Token Index: 141

Text #5

Max Range: 5.1581. Min Range: -5.1581

Max Act: 5.0482. Min Act: -0.1700

Data Index: 1051240 (Open Web Text)

Max Activating Token Index: 410

Text #6

Max Range: 5.1581. Min Range: -5.1581

Max Act: 5.0584. Min Act: -0.1700

Data Index: 8074437 (Open Web Text)

Max Activating Token Index: 291

Text #7

Max Range: 5.1581. Min Range: -5.1581

Max Act: 5.0388. Min Act: -0.1700

Data Index: 6197010 (Open Web Text)

Max Activating Token Index: 396

Text #8

Max Range: 5.1581. Min Range: -5.1581

Max Act: 5.0207. Min Act: -0.1700

Data Index: 1289040 (Open Web Text)

Max Activating Token Index: 50

Text #9

Max Range: 5.1581. Min Range: -5.1581

Max Act: 5.0202. Min Act: -0.1700

Data Index: 3745340 (Open Web Text)

Max Activating Token Index: 382

Text #10

Max Range: 5.1581. Min Range: -5.1581

Max Act: 4.9696. Min Act: -0.1700

Data Index: 4088980 (Open Web Text)

Max Activating Token Index: 108

Text #11

Max Range: 5.1581. Min Range: -5.1581

Max Act: 4.9991. Min Act: -0.1700

Data Index: 4391257 (Open Web Text)

Max Activating Token Index: 791

Text #12

Max Range: 5.1581. Min Range: -5.1581

Max Act: 4.9802. Min Act: -0.1700

Data Index: 2914312 (Open Web Text)

Max Activating Token Index: 315

Text #13

Max Range: 5.1581. Min Range: -5.1581

Max Act: 4.9681. Min Act: -0.1700

Data Index: 6782710 (Open Web Text)

Max Activating Token Index: 44

Text #14

Max Range: 5.1581. Min Range: -5.1581

Max Act: 4.9391. Min Act: -0.1700

Data Index: 6241045 (Open Web Text)

Max Activating Token Index: 137

Text #15

Max Range: 5.1581. Min Range: -5.1581

Max Act: 4.9797. Min Act: -0.1700

Data Index: 8085705 (Open Web Text)

Max Activating Token Index: 514

Text #16

Max Range: 5.1581. Min Range: -5.1581

Max Act: 4.9687. Min Act: -0.1700

Data Index: 8424521 (Open Web Text)

Max Activating Token Index: 203

Text #17

Max Range: 5.1581. Min Range: -5.1581

Max Act: 4.9451. Min Act: -0.1700

Data Index: 6072142 (Open Web Text)

Max Activating Token Index: 675

Text #18

Max Range: 5.1581. Min Range: -5.1581

Max Act: 4.9392. Min Act: -0.1700

Data Index: 507974 (Open Web Text)

Max Activating Token Index: 35

Text #19

Max Range: 5.1581. Min Range: -5.1581

Max Act: 4.9210. Min Act: -0.1700

Data Index: 1112751 (Open Web Text)

Max Activating Token Index: 520