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

Dataset: Open Web Text

Neuron 1295 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: 3.5826. Min Range: -3.5826

Max Act: 3.5826. Min Act: -0.1700

Data Index: 6716257 (Open Web Text)

Max Activating Token Index: 176

Text #1

Max Range: 3.5826. Min Range: -3.5826

Max Act: 3.5733. Min Act: -0.1700

Data Index: 6716258 (Open Web Text)

Max Activating Token Index: 259

Text #2

Max Range: 3.5826. Min Range: -3.5826

Max Act: 3.5117. Min Act: -0.1700

Data Index: 6716256 (Open Web Text)

Max Activating Token Index: 651

Text #3

Max Range: 3.5826. Min Range: -3.5826

Max Act: 3.4970. Min Act: -0.1700

Data Index: 2915126 (Open Web Text)

Max Activating Token Index: 635

Text #4

Max Range: 3.5826. Min Range: -3.5826

Max Act: 3.4649. Min Act: -0.1700

Data Index: 955637 (Open Web Text)

Max Activating Token Index: 283

Text #5

Max Range: 3.5826. Min Range: -3.5826

Max Act: 3.4906. Min Act: -0.1700

Data Index: 3339988 (Open Web Text)

Max Activating Token Index: 47

Text #6

Max Range: 3.5826. Min Range: -3.5826

Max Act: 3.4940. Min Act: -0.1700

Data Index: 6309937 (Open Web Text)

Max Activating Token Index: 419

Text #7

Max Range: 3.5826. Min Range: -3.5826

Max Act: 3.4967. Min Act: -0.1700

Data Index: 1198985 (Open Web Text)

Max Activating Token Index: 214

Text #8

Max Range: 3.5826. Min Range: -3.5826

Max Act: 3.4985. Min Act: -0.1700

Data Index: 2522905 (Open Web Text)

Max Activating Token Index: 507

Text #9

Max Range: 3.5826. Min Range: -3.5826

Max Act: 3.4541. Min Act: -0.1700

Data Index: 3201616 (Open Web Text)

Max Activating Token Index: 66

Text #10

Max Range: 3.5826. Min Range: -3.5826

Max Act: 3.4443. Min Act: -0.1700

Data Index: 6074250 (Open Web Text)

Max Activating Token Index: 785

Text #11

Max Range: 3.5826. Min Range: -3.5826

Max Act: 3.4440. Min Act: -0.1700

Data Index: 6313739 (Open Web Text)

Max Activating Token Index: 114

Text #12

Max Range: 3.5826. Min Range: -3.5826

Max Act: 3.4508. Min Act: -0.1700

Data Index: 5314858 (Open Web Text)

Max Activating Token Index: 963

Text #13

Max Range: 3.5826. Min Range: -3.5826

Max Act: 3.4382. Min Act: -0.1700

Data Index: 1344896 (Open Web Text)

Max Activating Token Index: 257

Text #14

Max Range: 3.5826. Min Range: -3.5826

Max Act: 3.4547. Min Act: -0.1700

Data Index: 2734885 (Open Web Text)

Max Activating Token Index: 383

Text #15

Max Range: 3.5826. Min Range: -3.5826

Max Act: 3.4209. Min Act: -0.1700

Data Index: 5985798 (Open Web Text)

Max Activating Token Index: 80

Text #16

Max Range: 3.5826. Min Range: -3.5826

Max Act: 3.4354. Min Act: -0.1700

Data Index: 5791076 (Open Web Text)

Max Activating Token Index: 332

Text #17

Max Range: 3.5826. Min Range: -3.5826

Max Act: 3.4267. Min Act: -0.1700

Data Index: 6381921 (Open Web Text)

Max Activating Token Index: 973

Text #18

Max Range: 3.5826. Min Range: -3.5826

Max Act: 3.4195. Min Act: -0.1700

Data Index: 6711153 (Open Web Text)

Max Activating Token Index: 465

Text #19

Max Range: 3.5826. Min Range: -3.5826

Max Act: 3.4427. Min Act: -0.1700

Data Index: 5314857 (Open Web Text)

Max Activating Token Index: 949