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

Dataset: Open Web Text

Neuron 961 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: 3.4472. Min Range: -3.4472

Max Act: 3.4405. Min Act: -0.1700

Data Index: 1596187 (Open Web Text)

Max Activating Token Index: 258

Text #1

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.4472. Min Act: -0.1700

Data Index: 496912 (Open Web Text)

Max Activating Token Index: 618

Text #2

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.4118. Min Act: -0.1700

Data Index: 20776 (Open Web Text)

Max Activating Token Index: 603

Text #3

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.4022. Min Act: -0.1700

Data Index: 7795524 (Open Web Text)

Max Activating Token Index: 353

Text #4

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.3704. Min Act: -0.1700

Data Index: 4768586 (Open Web Text)

Max Activating Token Index: 564

Text #5

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.3859. Min Act: -0.1700

Data Index: 7053156 (Open Web Text)

Max Activating Token Index: 279

Text #6

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.3679. Min Act: -0.1700

Data Index: 6556889 (Open Web Text)

Max Activating Token Index: 838

Text #7

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.3508. Min Act: -0.1700

Data Index: 5741856 (Open Web Text)

Max Activating Token Index: 395

Text #8

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.3607. Min Act: -0.1700

Data Index: 2001753 (Open Web Text)

Max Activating Token Index: 291

Text #9

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.3167. Min Act: -0.1700

Data Index: 1280716 (Open Web Text)

Max Activating Token Index: 745

Text #10

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.3235. Min Act: -0.1700

Data Index: 1543257 (Open Web Text)

Max Activating Token Index: 338

Text #11

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.3269. Min Act: -0.1700

Data Index: 673097 (Open Web Text)

Max Activating Token Index: 173

Text #12

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.3048. Min Act: -0.1700

Data Index: 4719942 (Open Web Text)

Max Activating Token Index: 471

Text #13

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.2971. Min Act: -0.1700

Data Index: 2302648 (Open Web Text)

Max Activating Token Index: 762

Text #14

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.2962. Min Act: -0.1700

Data Index: 6443439 (Open Web Text)

Max Activating Token Index: 293

Text #15

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.2790. Min Act: -0.1700

Data Index: 7796298 (Open Web Text)

Max Activating Token Index: 720

Text #16

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.2989. Min Act: -0.1700

Data Index: 7383717 (Open Web Text)

Max Activating Token Index: 48

Text #17

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.2846. Min Act: -0.1700

Data Index: 5739280 (Open Web Text)

Max Activating Token Index: 851

Text #18

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.2845. Min Act: -0.1700

Data Index: 5970761 (Open Web Text)

Max Activating Token Index: 673

Text #19

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.2730. Min Act: -0.1700

Data Index: 5936743 (Open Web Text)

Max Activating Token Index: 951