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

Dataset: Open Web Text

Neuron 2126 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: 2.1950. Min Range: -2.1950

Max Act: 2.1950. Min Act: -0.1700

Data Index: 747259 (Open Web Text)

Max Activating Token Index: 543

Text #1

Max Range: 2.1950. Min Range: -2.1950

Max Act: 2.1197. Min Act: -0.1700

Data Index: 973052 (Open Web Text)

Max Activating Token Index: 249

Text #2

Max Range: 2.1950. Min Range: -2.1950

Max Act: 2.0652. Min Act: -0.1700

Data Index: 346375 (Open Web Text)

Max Activating Token Index: 542

Text #3

Max Range: 2.1950. Min Range: -2.1950

Max Act: 2.0741. Min Act: -0.1700

Data Index: 6013689 (Open Web Text)

Max Activating Token Index: 260

Text #4

Max Range: 2.1950. Min Range: -2.1950

Max Act: 2.0662. Min Act: -0.1700

Data Index: 1253635 (Open Web Text)

Max Activating Token Index: 430

Text #5

Max Range: 2.1950. Min Range: -2.1950

Max Act: 2.0515. Min Act: -0.1700

Data Index: 1666090 (Open Web Text)

Max Activating Token Index: 903

Text #6

Max Range: 2.1950. Min Range: -2.1950

Max Act: 2.0517. Min Act: -0.1700

Data Index: 5918254 (Open Web Text)

Max Activating Token Index: 34

Text #7

Max Range: 2.1950. Min Range: -2.1950

Max Act: 2.0498. Min Act: -0.1700

Data Index: 3371088 (Open Web Text)

Max Activating Token Index: 240

Text #8

Max Range: 2.1950. Min Range: -2.1950

Max Act: 2.0467. Min Act: -0.1700

Data Index: 195098 (Open Web Text)

Max Activating Token Index: 69

Text #9

Max Range: 2.1950. Min Range: -2.1950

Max Act: 2.0304. Min Act: -0.1700

Data Index: 510963 (Open Web Text)

Max Activating Token Index: 648

Text #10

Max Range: 2.1950. Min Range: -2.1950

Max Act: 2.0383. Min Act: -0.1700

Data Index: 4537414 (Open Web Text)

Max Activating Token Index: 186

Text #11

Max Range: 2.1950. Min Range: -2.1950

Max Act: 2.0277. Min Act: -0.1700

Data Index: 195097 (Open Web Text)

Max Activating Token Index: 704

Text #12

Max Range: 2.1950. Min Range: -2.1950

Max Act: 2.0375. Min Act: -0.1700

Data Index: 2626961 (Open Web Text)

Max Activating Token Index: 930

Text #13

Max Range: 2.1950. Min Range: -2.1950

Max Act: 2.0332. Min Act: -0.1700

Data Index: 7607327 (Open Web Text)

Max Activating Token Index: 181

Text #14

Max Range: 2.1950. Min Range: -2.1950

Max Act: 2.0318. Min Act: -0.1700

Data Index: 408982 (Open Web Text)

Max Activating Token Index: 793

Text #15

Max Range: 2.1950. Min Range: -2.1950

Max Act: 2.0506. Min Act: -0.1700

Data Index: 6211820 (Open Web Text)

Max Activating Token Index: 132

Text #16

Max Range: 2.1950. Min Range: -2.1950

Max Act: 2.0362. Min Act: -0.1700

Data Index: 4583989 (Open Web Text)

Max Activating Token Index: 431

Text #17

Max Range: 2.1950. Min Range: -2.1950

Max Act: 2.0250. Min Act: -0.1700

Data Index: 227457 (Open Web Text)

Max Activating Token Index: 123

Text #18

Max Range: 2.1950. Min Range: -2.1950

Max Act: 2.0314. Min Act: -0.1700

Data Index: 2703829 (Open Web Text)

Max Activating Token Index: 888

Text #19

Max Range: 2.1950. Min Range: -2.1950

Max Act: 2.0194. Min Act: -0.1700

Data Index: 2838859 (Open Web Text)

Max Activating Token Index: 418