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

Dataset: Open Web Text

Neuron 160 in Layer 1

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: 4.3822. Min Range: -4.3822

Max Act: 4.3822. Min Act: -0.1700

Data Index: 2891941 (Open Web Text)

Max Activating Token Index: 676

Text #1

Max Range: 4.3822. Min Range: -4.3822

Max Act: 4.3518. Min Act: -0.1700

Data Index: 7128445 (Open Web Text)

Max Activating Token Index: 570

Text #2

Max Range: 4.3822. Min Range: -4.3822

Max Act: 4.3213. Min Act: -0.1700

Data Index: 1052889 (Open Web Text)

Max Activating Token Index: 659

Text #3

Max Range: 4.3822. Min Range: -4.3822

Max Act: 4.3281. Min Act: -0.1700

Data Index: 8152547 (Open Web Text)

Max Activating Token Index: 800

Text #4

Max Range: 4.3822. Min Range: -4.3822

Max Act: 4.3179. Min Act: -0.1700

Data Index: 7675403 (Open Web Text)

Max Activating Token Index: 622

Text #5

Max Range: 4.3822. Min Range: -4.3822

Max Act: 4.3097. Min Act: -0.1700

Data Index: 1403710 (Open Web Text)

Max Activating Token Index: 464

Text #6

Max Range: 4.3822. Min Range: -4.3822

Max Act: 4.2853. Min Act: -0.1700

Data Index: 1609085 (Open Web Text)

Max Activating Token Index: 542

Text #7

Max Range: 4.3822. Min Range: -4.3822

Max Act: 4.2979. Min Act: -0.1700

Data Index: 5107535 (Open Web Text)

Max Activating Token Index: 207

Text #8

Max Range: 4.3822. Min Range: -4.3822

Max Act: 4.2919. Min Act: -0.1700

Data Index: 4364294 (Open Web Text)

Max Activating Token Index: 221

Text #9

Max Range: 4.3822. Min Range: -4.3822

Max Act: 4.2805. Min Act: -0.1700

Data Index: 8143939 (Open Web Text)

Max Activating Token Index: 227

Text #10

Max Range: 4.3822. Min Range: -4.3822

Max Act: 4.2999. Min Act: -0.1700

Data Index: 4731070 (Open Web Text)

Max Activating Token Index: 604

Text #11

Max Range: 4.3822. Min Range: -4.3822

Max Act: 4.2548. Min Act: -0.1700

Data Index: 5332560 (Open Web Text)

Max Activating Token Index: 780

Text #12

Max Range: 4.3822. Min Range: -4.3822

Max Act: 4.2763. Min Act: -0.1700

Data Index: 990560 (Open Web Text)

Max Activating Token Index: 526

Text #13

Max Range: 4.3822. Min Range: -4.3822

Max Act: 4.2384. Min Act: -0.1700

Data Index: 631771 (Open Web Text)

Max Activating Token Index: 320

Text #14

Max Range: 4.3822. Min Range: -4.3822

Max Act: 4.2704. Min Act: -0.1700

Data Index: 1865453 (Open Web Text)

Max Activating Token Index: 600

Text #15

Max Range: 4.3822. Min Range: -4.3822

Max Act: 4.2817. Min Act: -0.1700

Data Index: 3817828 (Open Web Text)

Max Activating Token Index: 158

Text #16

Max Range: 4.3822. Min Range: -4.3822

Max Act: 4.2502. Min Act: -0.1700

Data Index: 5799344 (Open Web Text)

Max Activating Token Index: 409

Text #17

Max Range: 4.3822. Min Range: -4.3822

Max Act: 4.2386. Min Act: -0.1700

Data Index: 1243950 (Open Web Text)

Max Activating Token Index: 222

Text #18

Max Range: 4.3822. Min Range: -4.3822

Max Act: 4.2485. Min Act: -0.1700

Data Index: 2743100 (Open Web Text)

Max Activating Token Index: 281

Text #19

Max Range: 4.3822. Min Range: -4.3822

Max Act: 4.2546. Min Act: -0.1700

Data Index: 2878754 (Open Web Text)

Max Activating Token Index: 442