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

Dataset: Open Web Text

Neuron 2667 in Layer 1

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: 3.8494. Min Range: -3.8494

Max Act: 3.8494. Min Act: -0.1700

Data Index: 116277 (Open Web Text)

Max Activating Token Index: 480

Text #1

Max Range: 3.8494. Min Range: -3.8494

Max Act: 3.8363. Min Act: -0.1700

Data Index: 1644843 (Open Web Text)

Max Activating Token Index: 303

Text #2

Max Range: 3.8494. Min Range: -3.8494

Max Act: 3.8001. Min Act: -0.1700

Data Index: 7976795 (Open Web Text)

Max Activating Token Index: 625

Text #3

Max Range: 3.8494. Min Range: -3.8494

Max Act: 3.8050. Min Act: -0.1700

Data Index: 4759491 (Open Web Text)

Max Activating Token Index: 208

Text #4

Max Range: 3.8494. Min Range: -3.8494

Max Act: 3.7969. Min Act: -0.1700

Data Index: 2672181 (Open Web Text)

Max Activating Token Index: 174

Text #5

Max Range: 3.8494. Min Range: -3.8494

Max Act: 3.8081. Min Act: -0.1700

Data Index: 4196365 (Open Web Text)

Max Activating Token Index: 700

Text #6

Max Range: 3.8494. Min Range: -3.8494

Max Act: 3.8115. Min Act: -0.1700

Data Index: 4316339 (Open Web Text)

Max Activating Token Index: 108

Text #7

Max Range: 3.8494. Min Range: -3.8494

Max Act: 3.7630. Min Act: -0.1700

Data Index: 8109524 (Open Web Text)

Max Activating Token Index: 84

Text #8

Max Range: 3.8494. Min Range: -3.8494

Max Act: 3.7543. Min Act: -0.1700

Data Index: 7663521 (Open Web Text)

Max Activating Token Index: 495

Text #9

Max Range: 3.8494. Min Range: -3.8494

Max Act: 3.7702. Min Act: -0.1700

Data Index: 7613577 (Open Web Text)

Max Activating Token Index: 657

Text #10

Max Range: 3.8494. Min Range: -3.8494

Max Act: 3.7804. Min Act: -0.1700

Data Index: 6503437 (Open Web Text)

Max Activating Token Index: 608

Text #11

Max Range: 3.8494. Min Range: -3.8494

Max Act: 3.7621. Min Act: -0.1700

Data Index: 6306134 (Open Web Text)

Max Activating Token Index: 1010

Text #12

Max Range: 3.8494. Min Range: -3.8494

Max Act: 3.7759. Min Act: -0.1700

Data Index: 3604156 (Open Web Text)

Max Activating Token Index: 707

Text #13

Max Range: 3.8494. Min Range: -3.8494

Max Act: 3.7366. Min Act: -0.1700

Data Index: 4313995 (Open Web Text)

Max Activating Token Index: 483

Text #14

Max Range: 3.8494. Min Range: -3.8494

Max Act: 3.7252. Min Act: -0.1700

Data Index: 2213286 (Open Web Text)

Max Activating Token Index: 591

Text #15

Max Range: 3.8494. Min Range: -3.8494

Max Act: 3.7338. Min Act: -0.1700

Data Index: 7217204 (Open Web Text)

Max Activating Token Index: 291

Text #16

Max Range: 3.8494. Min Range: -3.8494

Max Act: 3.7369. Min Act: -0.1700

Data Index: 2641996 (Open Web Text)

Max Activating Token Index: 84

Text #17

Max Range: 3.8494. Min Range: -3.8494

Max Act: 3.7316. Min Act: -0.1700

Data Index: 6143535 (Open Web Text)

Max Activating Token Index: 109

Text #18

Max Range: 3.8494. Min Range: -3.8494

Max Act: 3.7362. Min Act: -0.1700

Data Index: 658027 (Open Web Text)

Max Activating Token Index: 275

Text #19

Max Range: 3.8494. Min Range: -3.8494

Max Act: 3.7451. Min Act: -0.1700

Data Index: 5540485 (Open Web Text)

Max Activating Token Index: 424