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

Dataset: Open Web Text

Neuron 1779 in Layer 1

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: 1.6315. Min Range: -1.6315

Max Act: 1.6315. Min Act: -0.1700

Data Index: 5059573 (Open Web Text)

Max Activating Token Index: 519

Text #1

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.6230. Min Act: -0.1700

Data Index: 1601929 (Open Web Text)

Max Activating Token Index: 105

Text #2

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.6183. Min Act: -0.1700

Data Index: 243469 (Open Web Text)

Max Activating Token Index: 508

Text #3

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.6054. Min Act: -0.1700

Data Index: 4924648 (Open Web Text)

Max Activating Token Index: 947

Text #4

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.5988. Min Act: -0.1700

Data Index: 8306861 (Open Web Text)

Max Activating Token Index: 392

Text #5

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.6033. Min Act: -0.1700

Data Index: 3695348 (Open Web Text)

Max Activating Token Index: 1020

Text #6

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.6042. Min Act: -0.1700

Data Index: 5139334 (Open Web Text)

Max Activating Token Index: 178

Text #7

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.6036. Min Act: -0.1700

Data Index: 521366 (Open Web Text)

Max Activating Token Index: 362

Text #8

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.6016. Min Act: -0.1700

Data Index: 7348176 (Open Web Text)

Max Activating Token Index: 16

Text #9

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.5932. Min Act: -0.1700

Data Index: 60451 (Open Web Text)

Max Activating Token Index: 97

Text #10

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.5909. Min Act: -0.1700

Data Index: 2444740 (Open Web Text)

Max Activating Token Index: 944

Text #11

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.5888. Min Act: -0.1700

Data Index: 4347478 (Open Web Text)

Max Activating Token Index: 699

Text #12

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.5915. Min Act: -0.1700

Data Index: 3888806 (Open Web Text)

Max Activating Token Index: 156

Text #13

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.5912. Min Act: -0.1700

Data Index: 7343665 (Open Web Text)

Max Activating Token Index: 515

Text #14

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.5854. Min Act: -0.1700

Data Index: 4084722 (Open Web Text)

Max Activating Token Index: 523

Text #15

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.5896. Min Act: -0.1700

Data Index: 4126474 (Open Web Text)

Max Activating Token Index: 263

Text #16

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.5879. Min Act: -0.1699

Data Index: 2130501 (Open Web Text)

Max Activating Token Index: 214

Text #17

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.5894. Min Act: -0.1700

Data Index: 2910446 (Open Web Text)

Max Activating Token Index: 553

Text #18

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.5895. Min Act: -0.1700

Data Index: 345724 (Open Web Text)

Max Activating Token Index: 624

Text #19

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.5843. Min Act: -0.1700

Data Index: 8375951 (Open Web Text)

Max Activating Token Index: 511