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

Dataset: Open Web Text

Neuron 1608 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: 3.0702. Min Range: -3.0702

Max Act: 3.0702. Min Act: -0.1700

Data Index: 8378953 (Open Web Text)

Max Activating Token Index: 910

Text #1

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.9398. Min Act: -0.1700

Data Index: 6419302 (Open Web Text)

Max Activating Token Index: 257

Text #2

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.9152. Min Act: -0.1700

Data Index: 221213 (Open Web Text)

Max Activating Token Index: 959

Text #3

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.9008. Min Act: -0.1700

Data Index: 7192139 (Open Web Text)

Max Activating Token Index: 183

Text #4

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.9021. Min Act: -0.1700

Data Index: 2902061 (Open Web Text)

Max Activating Token Index: 231

Text #5

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.8816. Min Act: -0.1700

Data Index: 6966316 (Open Web Text)

Max Activating Token Index: 154

Text #6

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.9034. Min Act: -0.1700

Data Index: 410771 (Open Web Text)

Max Activating Token Index: 810

Text #7

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.8613. Min Act: -0.1700

Data Index: 6549914 (Open Web Text)

Max Activating Token Index: 415

Text #8

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.8407. Min Act: -0.1700

Data Index: 4736342 (Open Web Text)

Max Activating Token Index: 602

Text #9

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.8404. Min Act: -0.1700

Data Index: 6224773 (Open Web Text)

Max Activating Token Index: 865

Text #10

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.8615. Min Act: -0.1700

Data Index: 3540191 (Open Web Text)

Max Activating Token Index: 947

Text #11

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.8521. Min Act: -0.1700

Data Index: 2806499 (Open Web Text)

Max Activating Token Index: 581

Text #12

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.8444. Min Act: -0.1700

Data Index: 8489915 (Open Web Text)

Max Activating Token Index: 293

Text #13

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.8480. Min Act: -0.1700

Data Index: 7466536 (Open Web Text)

Max Activating Token Index: 563

Text #14

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.8342. Min Act: -0.1700

Data Index: 1418997 (Open Web Text)

Max Activating Token Index: 880

Text #15

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.8331. Min Act: -0.1700

Data Index: 2917748 (Open Web Text)

Max Activating Token Index: 99

Text #16

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.8394. Min Act: -0.1700

Data Index: 7481136 (Open Web Text)

Max Activating Token Index: 783

Text #17

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.8112. Min Act: -0.1700

Data Index: 7514969 (Open Web Text)

Max Activating Token Index: 978

Text #18

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.8098. Min Act: -0.1700

Data Index: 3439797 (Open Web Text)

Max Activating Token Index: 314

Text #19

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.8118. Min Act: -0.1700

Data Index: 5376338 (Open Web Text)

Max Activating Token Index: 530