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

Dataset: Open Web Text

Neuron 11 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: 3.4522. Min Range: -3.4522

Max Act: 3.4522. Min Act: -0.1700

Data Index: 204949 (Open Web Text)

Max Activating Token Index: 801

Text #1

Max Range: 3.4522. Min Range: -3.4522

Max Act: 3.3598. Min Act: -0.1700

Data Index: 6653973 (Open Web Text)

Max Activating Token Index: 396

Text #2

Max Range: 3.4522. Min Range: -3.4522

Max Act: 3.3364. Min Act: -0.1700

Data Index: 573531 (Open Web Text)

Max Activating Token Index: 580

Text #3

Max Range: 3.4522. Min Range: -3.4522

Max Act: 3.3262. Min Act: -0.1700

Data Index: 7717132 (Open Web Text)

Max Activating Token Index: 604

Text #4

Max Range: 3.4522. Min Range: -3.4522

Max Act: 3.2591. Min Act: -0.1700

Data Index: 3404462 (Open Web Text)

Max Activating Token Index: 990

Text #5

Max Range: 3.4522. Min Range: -3.4522

Max Act: 3.2190. Min Act: -0.1700

Data Index: 3885119 (Open Web Text)

Max Activating Token Index: 469

Text #6

Max Range: 3.4522. Min Range: -3.4522

Max Act: 3.2466. Min Act: -0.1700

Data Index: 7443641 (Open Web Text)

Max Activating Token Index: 1015

Text #7

Max Range: 3.4522. Min Range: -3.4522

Max Act: 3.2513. Min Act: -0.1700

Data Index: 2810454 (Open Web Text)

Max Activating Token Index: 960

Text #8

Max Range: 3.4522. Min Range: -3.4522

Max Act: 3.2312. Min Act: -0.1700

Data Index: 6644001 (Open Web Text)

Max Activating Token Index: 317

Text #9

Max Range: 3.4522. Min Range: -3.4522

Max Act: 3.2511. Min Act: -0.1700

Data Index: 7931064 (Open Web Text)

Max Activating Token Index: 684

Text #10

Max Range: 3.4522. Min Range: -3.4522

Max Act: 3.2498. Min Act: -0.1700

Data Index: 4086389 (Open Web Text)

Max Activating Token Index: 306

Text #11

Max Range: 3.4522. Min Range: -3.4522

Max Act: 3.2373. Min Act: -0.1700

Data Index: 2915624 (Open Web Text)

Max Activating Token Index: 768

Text #12

Max Range: 3.4522. Min Range: -3.4522

Max Act: 3.2341. Min Act: -0.1700

Data Index: 2525470 (Open Web Text)

Max Activating Token Index: 358

Text #13

Max Range: 3.4522. Min Range: -3.4522

Max Act: 3.2133. Min Act: -0.1700

Data Index: 7273662 (Open Web Text)

Max Activating Token Index: 945

Text #14

Max Range: 3.4522. Min Range: -3.4522

Max Act: 3.2039. Min Act: -0.1700

Data Index: 6260096 (Open Web Text)

Max Activating Token Index: 299

Text #15

Max Range: 3.4522. Min Range: -3.4522

Max Act: 3.2138. Min Act: -0.1700

Data Index: 1683400 (Open Web Text)

Max Activating Token Index: 967

Text #16

Max Range: 3.4522. Min Range: -3.4522

Max Act: 3.2228. Min Act: -0.1700

Data Index: 4435082 (Open Web Text)

Max Activating Token Index: 796

Text #17

Max Range: 3.4522. Min Range: -3.4522

Max Act: 3.2227. Min Act: -0.1700

Data Index: 7519980 (Open Web Text)

Max Activating Token Index: 934

Text #18

Max Range: 3.4522. Min Range: -3.4522

Max Act: 3.2451. Min Act: -0.1700

Data Index: 3260949 (Open Web Text)

Max Activating Token Index: 518

Text #19

Max Range: 3.4522. Min Range: -3.4522

Max Act: 3.2048. Min Act: -0.1700

Data Index: 261809 (Open Web Text)

Max Activating Token Index: 345