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

Dataset: Open Web Text

Neuron 2153 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: 4.3901. Min Range: -4.3901

Max Act: 4.3901. Min Act: -0.1700

Data Index: 5066738 (Open Web Text)

Max Activating Token Index: 733

Text #1

Max Range: 4.3901. Min Range: -4.3901

Max Act: 4.3895. Min Act: -0.1700

Data Index: 6784481 (Open Web Text)

Max Activating Token Index: 98

Text #2

Max Range: 4.3901. Min Range: -4.3901

Max Act: 4.2227. Min Act: -0.1700

Data Index: 7966759 (Open Web Text)

Max Activating Token Index: 950

Text #3

Max Range: 4.3901. Min Range: -4.3901

Max Act: 4.2054. Min Act: -0.1700

Data Index: 8099695 (Open Web Text)

Max Activating Token Index: 793

Text #4

Max Range: 4.3901. Min Range: -4.3901

Max Act: 4.1705. Min Act: -0.1700

Data Index: 3558686 (Open Web Text)

Max Activating Token Index: 668

Text #5

Max Range: 4.3901. Min Range: -4.3901

Max Act: 4.1397. Min Act: -0.1700

Data Index: 8349006 (Open Web Text)

Max Activating Token Index: 264

Text #6

Max Range: 4.3901. Min Range: -4.3901

Max Act: 4.1495. Min Act: -0.1700

Data Index: 44514 (Open Web Text)

Max Activating Token Index: 269

Text #7

Max Range: 4.3901. Min Range: -4.3901

Max Act: 4.1238. Min Act: -0.1700

Data Index: 2820082 (Open Web Text)

Max Activating Token Index: 253

Text #8

Max Range: 4.3901. Min Range: -4.3901

Max Act: 4.0924. Min Act: -0.1700

Data Index: 3951506 (Open Web Text)

Max Activating Token Index: 570

Text #9

Max Range: 4.3901. Min Range: -4.3901

Max Act: 4.1293. Min Act: -0.1700

Data Index: 1206783 (Open Web Text)

Max Activating Token Index: 644

Text #10

Max Range: 4.3901. Min Range: -4.3901

Max Act: 4.0944. Min Act: -0.1700

Data Index: 7040023 (Open Web Text)

Max Activating Token Index: 211

Text #11

Max Range: 4.3901. Min Range: -4.3901

Max Act: 4.0808. Min Act: -0.1700

Data Index: 2521337 (Open Web Text)

Max Activating Token Index: 862

Text #12

Max Range: 4.3901. Min Range: -4.3901

Max Act: 4.1122. Min Act: -0.1700

Data Index: 113347 (Open Web Text)

Max Activating Token Index: 887

Text #13

Max Range: 4.3901. Min Range: -4.3901

Max Act: 4.0402. Min Act: -0.1700

Data Index: 6571527 (Open Web Text)

Max Activating Token Index: 461

Text #14

Max Range: 4.3901. Min Range: -4.3901

Max Act: 4.0532. Min Act: -0.1700

Data Index: 1478944 (Open Web Text)

Max Activating Token Index: 730

Text #15

Max Range: 4.3901. Min Range: -4.3901

Max Act: 4.0572. Min Act: -0.1700

Data Index: 8190668 (Open Web Text)

Max Activating Token Index: 752

Text #16

Max Range: 4.3901. Min Range: -4.3901

Max Act: 4.0751. Min Act: -0.1700

Data Index: 4088958 (Open Web Text)

Max Activating Token Index: 537

Text #17

Max Range: 4.3901. Min Range: -4.3901

Max Act: 4.0493. Min Act: -0.1700

Data Index: 7918226 (Open Web Text)

Max Activating Token Index: 317

Text #18

Max Range: 4.3901. Min Range: -4.3901

Max Act: 4.0154. Min Act: -0.1700

Data Index: 6786438 (Open Web Text)

Max Activating Token Index: 398

Text #19

Max Range: 4.3901. Min Range: -4.3901

Max Act: 4.0401. Min Act: -0.1700

Data Index: 3840534 (Open Web Text)

Max Activating Token Index: 707