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

Dataset: Open Web Text

Neuron 2123 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: 3.0421. Min Range: -3.0421

Max Act: 3.0421. Min Act: -0.1700

Data Index: 1235117 (Open Web Text)

Max Activating Token Index: 311

Text #1

Max Range: 3.0421. Min Range: -3.0421

Max Act: 2.9807. Min Act: -0.1700

Data Index: 5463671 (Open Web Text)

Max Activating Token Index: 37

Text #2

Max Range: 3.0421. Min Range: -3.0421

Max Act: 2.9573. Min Act: -0.1700

Data Index: 5618913 (Open Web Text)

Max Activating Token Index: 691

Text #3

Max Range: 3.0421. Min Range: -3.0421

Max Act: 2.9543. Min Act: -0.1700

Data Index: 8386063 (Open Web Text)

Max Activating Token Index: 273

Text #4

Max Range: 3.0421. Min Range: -3.0421

Max Act: 2.9542. Min Act: -0.1700

Data Index: 6990345 (Open Web Text)

Max Activating Token Index: 920

Text #5

Max Range: 3.0421. Min Range: -3.0421

Max Act: 2.9293. Min Act: -0.1700

Data Index: 15492 (Open Web Text)

Max Activating Token Index: 345

Text #6

Max Range: 3.0421. Min Range: -3.0421

Max Act: 2.9108. Min Act: -0.1700

Data Index: 5166583 (Open Web Text)

Max Activating Token Index: 329

Text #7

Max Range: 3.0421. Min Range: -3.0421

Max Act: 2.9209. Min Act: -0.1700

Data Index: 1547542 (Open Web Text)

Max Activating Token Index: 726

Text #8

Max Range: 3.0421. Min Range: -3.0421

Max Act: 2.9141. Min Act: -0.1700

Data Index: 7018516 (Open Web Text)

Max Activating Token Index: 675

Text #9

Max Range: 3.0421. Min Range: -3.0421

Max Act: 2.9136. Min Act: -0.1700

Data Index: 933066 (Open Web Text)

Max Activating Token Index: 428

Text #10

Max Range: 3.0421. Min Range: -3.0421

Max Act: 2.8947. Min Act: -0.1700

Data Index: 6011035 (Open Web Text)

Max Activating Token Index: 326

Text #11

Max Range: 3.0421. Min Range: -3.0421

Max Act: 2.9015. Min Act: -0.1700

Data Index: 1932420 (Open Web Text)

Max Activating Token Index: 447

Text #12

Max Range: 3.0421. Min Range: -3.0421

Max Act: 2.8899. Min Act: -0.1700

Data Index: 578150 (Open Web Text)

Max Activating Token Index: 555

Text #13

Max Range: 3.0421. Min Range: -3.0421

Max Act: 2.8874. Min Act: -0.1700

Data Index: 4962501 (Open Web Text)

Max Activating Token Index: 894

Text #14

Max Range: 3.0421. Min Range: -3.0421

Max Act: 2.8741. Min Act: -0.1700

Data Index: 7018517 (Open Web Text)

Max Activating Token Index: 952

Text #15

Max Range: 3.0421. Min Range: -3.0421

Max Act: 2.8564. Min Act: -0.1700

Data Index: 757563 (Open Web Text)

Max Activating Token Index: 710

Text #16

Max Range: 3.0421. Min Range: -3.0421

Max Act: 2.8681. Min Act: -0.1700

Data Index: 7018503 (Open Web Text)

Max Activating Token Index: 433

Text #17

Max Range: 3.0421. Min Range: -3.0421

Max Act: 2.8756. Min Act: -0.1700

Data Index: 4595349 (Open Web Text)

Max Activating Token Index: 135

Text #18

Max Range: 3.0421. Min Range: -3.0421

Max Act: 2.8760. Min Act: -0.1700

Data Index: 5864349 (Open Web Text)

Max Activating Token Index: 896

Text #19

Max Range: 3.0421. Min Range: -3.0421

Max Act: 2.8573. Min Act: -0.1700

Data Index: 1692799 (Open Web Text)

Max Activating Token Index: 78