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

Dataset: Open Web Text

Neuron 520 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: 3.0414. Min Range: -3.0414

Max Act: 3.0414. Min Act: -0.1700

Data Index: 6373670 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.9296. Min Act: -0.1700

Data Index: 6413750 (Open Web Text)

Max Activating Token Index: 127

Text #2

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.9445. Min Act: -0.1700

Data Index: 82270 (Open Web Text)

Max Activating Token Index: 637

Text #3

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8692. Min Act: -0.1700

Data Index: 4514449 (Open Web Text)

Max Activating Token Index: 203

Text #4

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.9242. Min Act: -0.1700

Data Index: 2628967 (Open Web Text)

Max Activating Token Index: 714

Text #5

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8913. Min Act: -0.1700

Data Index: 3341089 (Open Web Text)

Max Activating Token Index: 637

Text #6

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8903. Min Act: -0.1700

Data Index: 137725 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8701. Min Act: -0.1700

Data Index: 8111114 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8568. Min Act: -0.1700

Data Index: 3119961 (Open Web Text)

Max Activating Token Index: 51

Text #9

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8933. Min Act: -0.1700

Data Index: 7038869 (Open Web Text)

Max Activating Token Index: 527

Text #10

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8472. Min Act: -0.1700

Data Index: 7625925 (Open Web Text)

Max Activating Token Index: 461

Text #11

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8537. Min Act: -0.1700

Data Index: 1677543 (Open Web Text)

Max Activating Token Index: 129

Text #12

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8400. Min Act: -0.1700

Data Index: 3961548 (Open Web Text)

Max Activating Token Index: 714

Text #13

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8408. Min Act: -0.1700

Data Index: 7601433 (Open Web Text)

Max Activating Token Index: 81

Text #14

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8552. Min Act: -0.1700

Data Index: 2508576 (Open Web Text)

Max Activating Token Index: 977

Text #15

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8581. Min Act: -0.1700

Data Index: 5420196 (Open Web Text)

Max Activating Token Index: 41

Text #16

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8608. Min Act: -0.1700

Data Index: 8052877 (Open Web Text)

Max Activating Token Index: 33

Text #17

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8808. Min Act: -0.1700

Data Index: 2388868 (Open Web Text)

Max Activating Token Index: 633

Text #18

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8341. Min Act: -0.1700

Data Index: 8493329 (Open Web Text)

Max Activating Token Index: 767

Text #19

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8248. Min Act: -0.1700

Data Index: 7579432 (Open Web Text)

Max Activating Token Index: 94