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

Dataset: Open Web Text

Neuron 370 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: 4.9990. Min Range: -4.9990

Max Act: 4.9990. Min Act: -0.1700

Data Index: 5060790 (Open Web Text)

Max Activating Token Index: 883

Text #1

Max Range: 4.9990. Min Range: -4.9990

Max Act: 4.8079. Min Act: -0.1700

Data Index: 1883798 (Open Web Text)

Max Activating Token Index: 478

Text #2

Max Range: 4.9990. Min Range: -4.9990

Max Act: 4.6647. Min Act: -0.1700

Data Index: 3980253 (Open Web Text)

Max Activating Token Index: 517

Text #3

Max Range: 4.9990. Min Range: -4.9990

Max Act: 4.7050. Min Act: -0.1700

Data Index: 7888199 (Open Web Text)

Max Activating Token Index: 367

Text #4

Max Range: 4.9990. Min Range: -4.9990

Max Act: 4.6657. Min Act: -0.1700

Data Index: 7923088 (Open Web Text)

Max Activating Token Index: 1011

Text #5

Max Range: 4.9990. Min Range: -4.9990

Max Act: 4.6491. Min Act: -0.1700

Data Index: 4153971 (Open Web Text)

Max Activating Token Index: 259

Text #6

Max Range: 4.9990. Min Range: -4.9990

Max Act: 4.5831. Min Act: -0.1700

Data Index: 5437253 (Open Web Text)

Max Activating Token Index: 611

Text #7

Max Range: 4.9990. Min Range: -4.9990

Max Act: 4.5680. Min Act: -0.1700

Data Index: 7751046 (Open Web Text)

Max Activating Token Index: 529

Text #8

Max Range: 4.9990. Min Range: -4.9990

Max Act: 4.5531. Min Act: -0.1700

Data Index: 3861506 (Open Web Text)

Max Activating Token Index: 342

Text #9

Max Range: 4.9990. Min Range: -4.9990

Max Act: 4.6223. Min Act: -0.1700

Data Index: 4915861 (Open Web Text)

Max Activating Token Index: 644

Text #10

Max Range: 4.9990. Min Range: -4.9990

Max Act: 4.5419. Min Act: -0.1700

Data Index: 3031140 (Open Web Text)

Max Activating Token Index: 600

Text #11

Max Range: 4.9990. Min Range: -4.9990

Max Act: 4.5649. Min Act: -0.1700

Data Index: 3036747 (Open Web Text)

Max Activating Token Index: 456

Text #12

Max Range: 4.9990. Min Range: -4.9990

Max Act: 4.5136. Min Act: -0.1700

Data Index: 6185060 (Open Web Text)

Max Activating Token Index: 351

Text #13

Max Range: 4.9990. Min Range: -4.9990

Max Act: 4.4905. Min Act: -0.1700

Data Index: 8301182 (Open Web Text)

Max Activating Token Index: 622

Text #14

Max Range: 4.9990. Min Range: -4.9990

Max Act: 4.4634. Min Act: -0.1700

Data Index: 270290 (Open Web Text)

Max Activating Token Index: 630

Text #15

Max Range: 4.9990. Min Range: -4.9990

Max Act: 4.4659. Min Act: -0.1700

Data Index: 1399456 (Open Web Text)

Max Activating Token Index: 448

Text #16

Max Range: 4.9990. Min Range: -4.9990

Max Act: 4.4802. Min Act: -0.1700

Data Index: 6043360 (Open Web Text)

Max Activating Token Index: 268

Text #17

Max Range: 4.9990. Min Range: -4.9990

Max Act: 4.4863. Min Act: -0.1700

Data Index: 607615 (Open Web Text)

Max Activating Token Index: 853

Text #18

Max Range: 4.9990. Min Range: -4.9990

Max Act: 4.4092. Min Act: -0.1700

Data Index: 1031729 (Open Web Text)

Max Activating Token Index: 625

Text #19

Max Range: 4.9990. Min Range: -4.9990

Max Act: 4.4171. Min Act: -0.1700

Data Index: 7966262 (Open Web Text)

Max Activating Token Index: 345