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

Dataset: Open Web Text

Neuron 206 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: 3.7980. Min Range: -3.7980

Max Act: 3.7754. Min Act: -0.1700

Data Index: 416788 (Open Web Text)

Max Activating Token Index: 969

Text #1

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.7980. Min Act: -0.1700

Data Index: 1360570 (Open Web Text)

Max Activating Token Index: 527

Text #2

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.7373. Min Act: -0.1700

Data Index: 28362 (Open Web Text)

Max Activating Token Index: 1020

Text #3

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.6841. Min Act: -0.1700

Data Index: 6755280 (Open Web Text)

Max Activating Token Index: 911

Text #4

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.6833. Min Act: -0.1700

Data Index: 7096137 (Open Web Text)

Max Activating Token Index: 771

Text #5

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.7297. Min Act: -0.1700

Data Index: 4377912 (Open Web Text)

Max Activating Token Index: 1011

Text #6

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.6749. Min Act: -0.1700

Data Index: 7507576 (Open Web Text)

Max Activating Token Index: 422

Text #7

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.6360. Min Act: -0.1700

Data Index: 6896706 (Open Web Text)

Max Activating Token Index: 427

Text #8

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.6618. Min Act: -0.1700

Data Index: 1845817 (Open Web Text)

Max Activating Token Index: 646

Text #9

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.6626. Min Act: -0.1700

Data Index: 2054585 (Open Web Text)

Max Activating Token Index: 628

Text #10

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.6381. Min Act: -0.1700

Data Index: 7507580 (Open Web Text)

Max Activating Token Index: 109

Text #11

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.6406. Min Act: -0.1700

Data Index: 6017540 (Open Web Text)

Max Activating Token Index: 931

Text #12

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.6171. Min Act: -0.1700

Data Index: 1746909 (Open Web Text)

Max Activating Token Index: 642

Text #13

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.5988. Min Act: -0.1700

Data Index: 3658366 (Open Web Text)

Max Activating Token Index: 852

Text #14

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.5920. Min Act: -0.1700

Data Index: 2698974 (Open Web Text)

Max Activating Token Index: 371

Text #15

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.6399. Min Act: -0.1700

Data Index: 6402926 (Open Web Text)

Max Activating Token Index: 995

Text #16

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.5996. Min Act: -0.1700

Data Index: 4301740 (Open Web Text)

Max Activating Token Index: 345

Text #17

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.5935. Min Act: -0.1700

Data Index: 1130853 (Open Web Text)

Max Activating Token Index: 205

Text #18

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.5761. Min Act: -0.1700

Data Index: 5763511 (Open Web Text)

Max Activating Token Index: 962

Text #19

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.5760. Min Act: -0.1700

Data Index: 4077337 (Open Web Text)

Max Activating Token Index: 260