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

Dataset: Open Web Text

Neuron 1604 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: 3.4356. Min Range: -3.4356

Max Act: 3.4286. Min Act: -0.1700

Data Index: 7777064 (Open Web Text)

Max Activating Token Index: 557

Text #1

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.4356. Min Act: -0.1700

Data Index: 3116803 (Open Web Text)

Max Activating Token Index: 565

Text #2

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.3316. Min Act: -0.1700

Data Index: 6018532 (Open Web Text)

Max Activating Token Index: 887

Text #3

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.3313. Min Act: -0.1700

Data Index: 1981070 (Open Web Text)

Max Activating Token Index: 1012

Text #4

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.3270. Min Act: -0.1700

Data Index: 8081947 (Open Web Text)

Max Activating Token Index: 251

Text #5

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.3171. Min Act: -0.1700

Data Index: 104891 (Open Web Text)

Max Activating Token Index: 236

Text #6

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.2986. Min Act: -0.1700

Data Index: 3190391 (Open Web Text)

Max Activating Token Index: 440

Text #7

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.2931. Min Act: -0.1700

Data Index: 6162509 (Open Web Text)

Max Activating Token Index: 682

Text #8

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.2957. Min Act: -0.1700

Data Index: 1411674 (Open Web Text)

Max Activating Token Index: 954

Text #9

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.2922. Min Act: -0.1700

Data Index: 5652364 (Open Web Text)

Max Activating Token Index: 798

Text #10

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.2940. Min Act: -0.1700

Data Index: 714473 (Open Web Text)

Max Activating Token Index: 919

Text #11

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.2950. Min Act: -0.1700

Data Index: 2646527 (Open Web Text)

Max Activating Token Index: 683

Text #12

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.2903. Min Act: -0.1700

Data Index: 6436052 (Open Web Text)

Max Activating Token Index: 387

Text #13

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.2762. Min Act: -0.1700

Data Index: 7226666 (Open Web Text)

Max Activating Token Index: 960

Text #14

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.2474. Min Act: -0.1700

Data Index: 8139616 (Open Web Text)

Max Activating Token Index: 847

Text #15

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.2353. Min Act: -0.1700

Data Index: 1268431 (Open Web Text)

Max Activating Token Index: 977

Text #16

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.2418. Min Act: -0.1700

Data Index: 6529898 (Open Web Text)

Max Activating Token Index: 490

Text #17

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.2291. Min Act: -0.1700

Data Index: 1476005 (Open Web Text)

Max Activating Token Index: 1004

Text #18

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.2471. Min Act: -0.1700

Data Index: 2685342 (Open Web Text)

Max Activating Token Index: 34

Text #19

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.2376. Min Act: -0.1700

Data Index: 3430512 (Open Web Text)

Max Activating Token Index: 70