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

Dataset: Open Web Text

Neuron 1522 in Layer 3

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: 3.6033. Min Range: -3.6033

Max Act: 3.5707. Min Act: -0.1700

Data Index: 2284353 (Open Web Text)

Max Activating Token Index: 83

Text #1

Max Range: 3.6033. Min Range: -3.6033

Max Act: 3.6033. Min Act: -0.1700

Data Index: 4180687 (Open Web Text)

Max Activating Token Index: 219

Text #2

Max Range: 3.6033. Min Range: -3.6033

Max Act: 3.5683. Min Act: -0.1700

Data Index: 4545121 (Open Web Text)

Max Activating Token Index: 912

Text #3

Max Range: 3.6033. Min Range: -3.6033

Max Act: 3.5513. Min Act: -0.1700

Data Index: 1037940 (Open Web Text)

Max Activating Token Index: 257

Text #4

Max Range: 3.6033. Min Range: -3.6033

Max Act: 3.5454. Min Act: -0.1700

Data Index: 2735408 (Open Web Text)

Max Activating Token Index: 640

Text #5

Max Range: 3.6033. Min Range: -3.6033

Max Act: 3.4979. Min Act: -0.1700

Data Index: 2424023 (Open Web Text)

Max Activating Token Index: 657

Text #6

Max Range: 3.6033. Min Range: -3.6033

Max Act: 3.4990. Min Act: -0.1700

Data Index: 156001 (Open Web Text)

Max Activating Token Index: 247

Text #7

Max Range: 3.6033. Min Range: -3.6033

Max Act: 3.4993. Min Act: -0.1700

Data Index: 3688703 (Open Web Text)

Max Activating Token Index: 514

Text #8

Max Range: 3.6033. Min Range: -3.6033

Max Act: 3.5130. Min Act: -0.1700

Data Index: 3396522 (Open Web Text)

Max Activating Token Index: 580

Text #9

Max Range: 3.6033. Min Range: -3.6033

Max Act: 3.4826. Min Act: -0.1700

Data Index: 2972761 (Open Web Text)

Max Activating Token Index: 973

Text #10

Max Range: 3.6033. Min Range: -3.6033

Max Act: 3.5137. Min Act: -0.1700

Data Index: 8623213 (Open Web Text)

Max Activating Token Index: 230

Text #11

Max Range: 3.6033. Min Range: -3.6033

Max Act: 3.4743. Min Act: -0.1700

Data Index: 7284607 (Open Web Text)

Max Activating Token Index: 290

Text #12

Max Range: 3.6033. Min Range: -3.6033

Max Act: 3.5102. Min Act: -0.1700

Data Index: 6404907 (Open Web Text)

Max Activating Token Index: 222

Text #13

Max Range: 3.6033. Min Range: -3.6033

Max Act: 3.4769. Min Act: -0.1700

Data Index: 3151193 (Open Web Text)

Max Activating Token Index: 253

Text #14

Max Range: 3.6033. Min Range: -3.6033

Max Act: 3.4697. Min Act: -0.1700

Data Index: 1442081 (Open Web Text)

Max Activating Token Index: 367

Text #15

Max Range: 3.6033. Min Range: -3.6033

Max Act: 3.4618. Min Act: -0.1700

Data Index: 2782102 (Open Web Text)

Max Activating Token Index: 184

Text #16

Max Range: 3.6033. Min Range: -3.6033

Max Act: 3.4738. Min Act: -0.1700

Data Index: 1724914 (Open Web Text)

Max Activating Token Index: 478

Text #17

Max Range: 3.6033. Min Range: -3.6033

Max Act: 3.4715. Min Act: -0.1700

Data Index: 3910448 (Open Web Text)

Max Activating Token Index: 473

Text #18

Max Range: 3.6033. Min Range: -3.6033

Max Act: 3.4440. Min Act: -0.1700

Data Index: 3931435 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 3.6033. Min Range: -3.6033

Max Act: 3.4595. Min Act: -0.1700

Data Index: 3990507 (Open Web Text)

Max Activating Token Index: 585