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

Dataset: Open Web Text

Neuron 2638 in Layer 4

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: 3.4766. Min Range: -3.4766

Max Act: 3.4766. Min Act: -0.1700

Data Index: 5691791 (Open Web Text)

Max Activating Token Index: 392

Text #1

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3881. Min Act: -0.1700

Data Index: 169605 (Open Web Text)

Max Activating Token Index: 308

Text #2

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3961. Min Act: -0.1700

Data Index: 8079606 (Open Web Text)

Max Activating Token Index: 276

Text #3

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3818. Min Act: -0.1700

Data Index: 3892191 (Open Web Text)

Max Activating Token Index: 329

Text #4

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3925. Min Act: -0.1700

Data Index: 310458 (Open Web Text)

Max Activating Token Index: 915

Text #5

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3829. Min Act: -0.1700

Data Index: 3622596 (Open Web Text)

Max Activating Token Index: 569

Text #6

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3732. Min Act: -0.1700

Data Index: 7235705 (Open Web Text)

Max Activating Token Index: 77

Text #7

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3686. Min Act: -0.1700

Data Index: 2189734 (Open Web Text)

Max Activating Token Index: 959

Text #8

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3763. Min Act: -0.1700

Data Index: 8409776 (Open Web Text)

Max Activating Token Index: 360

Text #9

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3463. Min Act: -0.1700

Data Index: 5869266 (Open Web Text)

Max Activating Token Index: 298

Text #10

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3112. Min Act: -0.1700

Data Index: 6350199 (Open Web Text)

Max Activating Token Index: 856

Text #11

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3236. Min Act: -0.1700

Data Index: 1857729 (Open Web Text)

Max Activating Token Index: 671

Text #12

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3283. Min Act: -0.1700

Data Index: 6424220 (Open Web Text)

Max Activating Token Index: 768

Text #13

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3232. Min Act: -0.1700

Data Index: 1809605 (Open Web Text)

Max Activating Token Index: 140

Text #14

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3012. Min Act: -0.1700

Data Index: 2290884 (Open Web Text)

Max Activating Token Index: 402

Text #15

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3188. Min Act: -0.1700

Data Index: 2306394 (Open Web Text)

Max Activating Token Index: 805

Text #16

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3396. Min Act: -0.1700

Data Index: 5911330 (Open Web Text)

Max Activating Token Index: 724

Text #17

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.2850. Min Act: -0.1700

Data Index: 5889602 (Open Web Text)

Max Activating Token Index: 947

Text #18

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3102. Min Act: -0.1700

Data Index: 4085523 (Open Web Text)

Max Activating Token Index: 566

Text #19

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3315. Min Act: -0.1700

Data Index: 4344586 (Open Web Text)

Max Activating Token Index: 874