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

Dataset: Open Web Text

Neuron 1035 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: 4.7622. Min Range: -4.7622

Max Act: 4.7622. Min Act: -0.1700

Data Index: 8584559 (Open Web Text)

Max Activating Token Index: 653

Text #1

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.6697. Min Act: -0.1700

Data Index: 6865662 (Open Web Text)

Max Activating Token Index: 521

Text #2

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.6660. Min Act: -0.1700

Data Index: 7456434 (Open Web Text)

Max Activating Token Index: 477

Text #3

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.6908. Min Act: -0.1700

Data Index: 5848562 (Open Web Text)

Max Activating Token Index: 69

Text #4

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.6871. Min Act: -0.1700

Data Index: 8587680 (Open Web Text)

Max Activating Token Index: 1017

Text #5

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.6451. Min Act: -0.1700

Data Index: 2149360 (Open Web Text)

Max Activating Token Index: 986

Text #6

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.6483. Min Act: -0.1700

Data Index: 5364870 (Open Web Text)

Max Activating Token Index: 759

Text #7

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.6704. Min Act: -0.1700

Data Index: 841581 (Open Web Text)

Max Activating Token Index: 1009

Text #8

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.6669. Min Act: -0.1700

Data Index: 2932135 (Open Web Text)

Max Activating Token Index: 801

Text #9

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.6445. Min Act: -0.1700

Data Index: 5043240 (Open Web Text)

Max Activating Token Index: 656

Text #10

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.6387. Min Act: -0.1700

Data Index: 3913550 (Open Web Text)

Max Activating Token Index: 517

Text #11

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.6451. Min Act: -0.1700

Data Index: 5848560 (Open Web Text)

Max Activating Token Index: 318

Text #12

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.6264. Min Act: -0.1700

Data Index: 1978981 (Open Web Text)

Max Activating Token Index: 348

Text #13

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.6517. Min Act: -0.1700

Data Index: 2560225 (Open Web Text)

Max Activating Token Index: 931

Text #14

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.6491. Min Act: -0.1700

Data Index: 2149362 (Open Web Text)

Max Activating Token Index: 737

Text #15

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.6655. Min Act: -0.1700

Data Index: 7698119 (Open Web Text)

Max Activating Token Index: 90

Text #16

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.6394. Min Act: -0.1700

Data Index: 6928870 (Open Web Text)

Max Activating Token Index: 419

Text #17

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.6037. Min Act: -0.1700

Data Index: 2083275 (Open Web Text)

Max Activating Token Index: 251

Text #18

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.6203. Min Act: -0.1700

Data Index: 5043238 (Open Web Text)

Max Activating Token Index: 905

Text #19

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.6153. Min Act: -0.1700

Data Index: 2560224 (Open Web Text)

Max Activating Token Index: 157