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

Dataset: Open Web Text

Neuron 393 in Layer 5

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: 3.0577. Min Range: -3.0577

Max Act: 3.0577. Min Act: -0.1700

Data Index: 8790641 (Open Web Text)

Max Activating Token Index: 900

Text #1

Max Range: 3.0577. Min Range: -3.0577

Max Act: 3.0334. Min Act: -0.1700

Data Index: 3676155 (Open Web Text)

Max Activating Token Index: 717

Text #2

Max Range: 3.0577. Min Range: -3.0577

Max Act: 2.9263. Min Act: -0.1700

Data Index: 3952335 (Open Web Text)

Max Activating Token Index: 217

Text #3

Max Range: 3.0577. Min Range: -3.0577

Max Act: 2.9281. Min Act: -0.1700

Data Index: 142843 (Open Web Text)

Max Activating Token Index: 783

Text #4

Max Range: 3.0577. Min Range: -3.0577

Max Act: 2.8835. Min Act: -0.1700

Data Index: 5307642 (Open Web Text)

Max Activating Token Index: 562

Text #5

Max Range: 3.0577. Min Range: -3.0577

Max Act: 2.9009. Min Act: -0.1700

Data Index: 5280544 (Open Web Text)

Max Activating Token Index: 911

Text #6

Max Range: 3.0577. Min Range: -3.0577

Max Act: 2.8702. Min Act: -0.1700

Data Index: 7461124 (Open Web Text)

Max Activating Token Index: 293

Text #7

Max Range: 3.0577. Min Range: -3.0577

Max Act: 2.8823. Min Act: -0.1700

Data Index: 6217344 (Open Web Text)

Max Activating Token Index: 482

Text #8

Max Range: 3.0577. Min Range: -3.0577

Max Act: 2.8772. Min Act: -0.1700

Data Index: 3928038 (Open Web Text)

Max Activating Token Index: 634

Text #9

Max Range: 3.0577. Min Range: -3.0577

Max Act: 2.8479. Min Act: -0.1700

Data Index: 8741754 (Open Web Text)

Max Activating Token Index: 566

Text #10

Max Range: 3.0577. Min Range: -3.0577

Max Act: 2.8642. Min Act: -0.1700

Data Index: 6278843 (Open Web Text)

Max Activating Token Index: 382

Text #11

Max Range: 3.0577. Min Range: -3.0577

Max Act: 2.8396. Min Act: -0.1700

Data Index: 689059 (Open Web Text)

Max Activating Token Index: 953

Text #12

Max Range: 3.0577. Min Range: -3.0577

Max Act: 2.8498. Min Act: -0.1700

Data Index: 3657944 (Open Web Text)

Max Activating Token Index: 516

Text #13

Max Range: 3.0577. Min Range: -3.0577

Max Act: 2.8449. Min Act: -0.1700

Data Index: 1201437 (Open Web Text)

Max Activating Token Index: 605

Text #14

Max Range: 3.0577. Min Range: -3.0577

Max Act: 2.8539. Min Act: -0.1700

Data Index: 1048053 (Open Web Text)

Max Activating Token Index: 154

Text #15

Max Range: 3.0577. Min Range: -3.0577

Max Act: 2.8266. Min Act: -0.1700

Data Index: 3543624 (Open Web Text)

Max Activating Token Index: 98

Text #16

Max Range: 3.0577. Min Range: -3.0577

Max Act: 2.8475. Min Act: -0.1700

Data Index: 8385212 (Open Web Text)

Max Activating Token Index: 907

Text #17

Max Range: 3.0577. Min Range: -3.0577

Max Act: 2.8559. Min Act: -0.1700

Data Index: 2330506 (Open Web Text)

Max Activating Token Index: 332

Text #18

Max Range: 3.0577. Min Range: -3.0577

Max Act: 2.8406. Min Act: -0.1700

Data Index: 2754669 (Open Web Text)

Max Activating Token Index: 302

Text #19

Max Range: 3.0577. Min Range: -3.0577

Max Act: 2.8606. Min Act: -0.1700

Data Index: 1180492 (Open Web Text)

Max Activating Token Index: 683