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

Dataset: Open Web Text

Neuron 1078 in Layer 6

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: 4.6969. Min Range: -4.6969

Max Act: 4.6872. Min Act: -0.1700

Data Index: 5538831 (Open Web Text)

Max Activating Token Index: 139

Text #1

Max Range: 4.6969. Min Range: -4.6969

Max Act: 4.6969. Min Act: -0.1700

Data Index: 6187284 (Open Web Text)

Max Activating Token Index: 444

Text #2

Max Range: 4.6969. Min Range: -4.6969

Max Act: 4.6242. Min Act: -0.1700

Data Index: 5897813 (Open Web Text)

Max Activating Token Index: 94

Text #3

Max Range: 4.6969. Min Range: -4.6969

Max Act: 4.4736. Min Act: -0.1700

Data Index: 3545878 (Open Web Text)

Max Activating Token Index: 410

Text #4

Max Range: 4.6969. Min Range: -4.6969

Max Act: 4.4425. Min Act: -0.1700

Data Index: 3610472 (Open Web Text)

Max Activating Token Index: 200

Text #5

Max Range: 4.6969. Min Range: -4.6969

Max Act: 4.4447. Min Act: -0.1700

Data Index: 6782216 (Open Web Text)

Max Activating Token Index: 759

Text #6

Max Range: 4.6969. Min Range: -4.6969

Max Act: 4.4183. Min Act: -0.1700

Data Index: 6302483 (Open Web Text)

Max Activating Token Index: 329

Text #7

Max Range: 4.6969. Min Range: -4.6969

Max Act: 4.4077. Min Act: -0.1700

Data Index: 4002035 (Open Web Text)

Max Activating Token Index: 192

Text #8

Max Range: 4.6969. Min Range: -4.6969

Max Act: 4.3765. Min Act: -0.1700

Data Index: 5431839 (Open Web Text)

Max Activating Token Index: 985

Text #9

Max Range: 4.6969. Min Range: -4.6969

Max Act: 4.3799. Min Act: -0.1700

Data Index: 2879327 (Open Web Text)

Max Activating Token Index: 842

Text #10

Max Range: 4.6969. Min Range: -4.6969

Max Act: 4.3837. Min Act: -0.1700

Data Index: 6265902 (Open Web Text)

Max Activating Token Index: 789

Text #11

Max Range: 4.6969. Min Range: -4.6969

Max Act: 4.3515. Min Act: -0.1700

Data Index: 6183049 (Open Web Text)

Max Activating Token Index: 801

Text #12

Max Range: 4.6969. Min Range: -4.6969

Max Act: 4.3556. Min Act: -0.1700

Data Index: 6589508 (Open Web Text)

Max Activating Token Index: 341

Text #13

Max Range: 4.6969. Min Range: -4.6969

Max Act: 4.3409. Min Act: -0.1700

Data Index: 6517558 (Open Web Text)

Max Activating Token Index: 801

Text #14

Max Range: 4.6969. Min Range: -4.6969

Max Act: 4.3310. Min Act: -0.1700

Data Index: 4814635 (Open Web Text)

Max Activating Token Index: 637

Text #15

Max Range: 4.6969. Min Range: -4.6969

Max Act: 4.3205. Min Act: -0.1700

Data Index: 7535246 (Open Web Text)

Max Activating Token Index: 888

Text #16

Max Range: 4.6969. Min Range: -4.6969

Max Act: 4.3268. Min Act: -0.1700

Data Index: 130800 (Open Web Text)

Max Activating Token Index: 366

Text #17

Max Range: 4.6969. Min Range: -4.6969

Max Act: 4.3309. Min Act: -0.1700

Data Index: 4460577 (Open Web Text)

Max Activating Token Index: 488

Text #18

Max Range: 4.6969. Min Range: -4.6969

Max Act: 4.3247. Min Act: -0.1700

Data Index: 4814632 (Open Web Text)

Max Activating Token Index: 334

Text #19

Max Range: 4.6969. Min Range: -4.6969

Max Act: 4.2950. Min Act: -0.1700

Data Index: 3921387 (Open Web Text)

Max Activating Token Index: 510