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

Dataset: Open Web Text

Neuron 1862 in Layer 2

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: 3.5500. Min Range: -3.5500

Max Act: 3.5500. Min Act: -0.1700

Data Index: 4814298 (Open Web Text)

Max Activating Token Index: 381

Text #1

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.5353. Min Act: -0.1700

Data Index: 7873041 (Open Web Text)

Max Activating Token Index: 389

Text #2

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.4901. Min Act: -0.1700

Data Index: 4758625 (Open Web Text)

Max Activating Token Index: 839

Text #3

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.4909. Min Act: -0.1700

Data Index: 3398339 (Open Web Text)

Max Activating Token Index: 167

Text #4

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.4564. Min Act: -0.1700

Data Index: 5260306 (Open Web Text)

Max Activating Token Index: 490

Text #5

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.4481. Min Act: -0.1700

Data Index: 3302256 (Open Web Text)

Max Activating Token Index: 348

Text #6

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.4485. Min Act: -0.1700

Data Index: 3635651 (Open Web Text)

Max Activating Token Index: 58

Text #7

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.4279. Min Act: -0.1700

Data Index: 6140887 (Open Web Text)

Max Activating Token Index: 801

Text #8

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.4074. Min Act: -0.1700

Data Index: 3039914 (Open Web Text)

Max Activating Token Index: 660

Text #9

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.4235. Min Act: -0.1700

Data Index: 4496891 (Open Web Text)

Max Activating Token Index: 941

Text #10

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.4367. Min Act: -0.1700

Data Index: 6249568 (Open Web Text)

Max Activating Token Index: 183

Text #11

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.4407. Min Act: -0.1700

Data Index: 7005803 (Open Web Text)

Max Activating Token Index: 780

Text #12

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.4081. Min Act: -0.1700

Data Index: 1157943 (Open Web Text)

Max Activating Token Index: 75

Text #13

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.3800. Min Act: -0.1700

Data Index: 555895 (Open Web Text)

Max Activating Token Index: 935

Text #14

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.3961. Min Act: -0.1700

Data Index: 5149510 (Open Web Text)

Max Activating Token Index: 379

Text #15

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.4056. Min Act: -0.1700

Data Index: 91898 (Open Web Text)

Max Activating Token Index: 508

Text #16

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.4058. Min Act: -0.1700

Data Index: 4830484 (Open Web Text)

Max Activating Token Index: 91

Text #17

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.3947. Min Act: -0.1700

Data Index: 2866862 (Open Web Text)

Max Activating Token Index: 385

Text #18

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.4101. Min Act: -0.1700

Data Index: 2893776 (Open Web Text)

Max Activating Token Index: 173

Text #19

Max Range: 3.5500. Min Range: -3.5500

Max Act: 3.4046. Min Act: -0.1700

Data Index: 4272893 (Open Web Text)

Max Activating Token Index: 16