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

Dataset: Open Web Text

Neuron 80 in Layer 2

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: 3.4028. Min Range: -3.4028

Max Act: 3.3917. Min Act: -0.1700

Data Index: 4925860 (Open Web Text)

Max Activating Token Index: 74

Text #1

Max Range: 3.4028. Min Range: -3.4028

Max Act: 3.3975. Min Act: -0.1700

Data Index: 1271395 (Open Web Text)

Max Activating Token Index: 540

Text #2

Max Range: 3.4028. Min Range: -3.4028

Max Act: 3.3994. Min Act: -0.1700

Data Index: 4233559 (Open Web Text)

Max Activating Token Index: 676

Text #3

Max Range: 3.4028. Min Range: -3.4028

Max Act: 3.4028. Min Act: -0.1700

Data Index: 4244518 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 3.4028. Min Range: -3.4028

Max Act: 3.3807. Min Act: -0.1700

Data Index: 77423 (Open Web Text)

Max Activating Token Index: 766

Text #5

Max Range: 3.4028. Min Range: -3.4028

Max Act: 3.3857. Min Act: -0.1700

Data Index: 331918 (Open Web Text)

Max Activating Token Index: 409

Text #6

Max Range: 3.4028. Min Range: -3.4028

Max Act: 3.3906. Min Act: -0.1700

Data Index: 906157 (Open Web Text)

Max Activating Token Index: 386

Text #7

Max Range: 3.4028. Min Range: -3.4028

Max Act: 3.3860. Min Act: -0.1700

Data Index: 1556733 (Open Web Text)

Max Activating Token Index: 365

Text #8

Max Range: 3.4028. Min Range: -3.4028

Max Act: 3.3744. Min Act: -0.1700

Data Index: 6796260 (Open Web Text)

Max Activating Token Index: 465

Text #9

Max Range: 3.4028. Min Range: -3.4028

Max Act: 3.3680. Min Act: -0.1700

Data Index: 529849 (Open Web Text)

Max Activating Token Index: 68

Text #10

Max Range: 3.4028. Min Range: -3.4028

Max Act: 3.3786. Min Act: -0.1700

Data Index: 4322878 (Open Web Text)

Max Activating Token Index: 640

Text #11

Max Range: 3.4028. Min Range: -3.4028

Max Act: 3.3867. Min Act: -0.1700

Data Index: 3798109 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 3.4028. Min Range: -3.4028

Max Act: 3.3747. Min Act: -0.1700

Data Index: 5606607 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 3.4028. Min Range: -3.4028

Max Act: 3.3706. Min Act: -0.1700

Data Index: 6600110 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 3.4028. Min Range: -3.4028

Max Act: 3.3511. Min Act: -0.1700

Data Index: 8457380 (Open Web Text)

Max Activating Token Index: 110

Text #15

Max Range: 3.4028. Min Range: -3.4028

Max Act: 3.3496. Min Act: -0.1700

Data Index: 915705 (Open Web Text)

Max Activating Token Index: 317

Text #16

Max Range: 3.4028. Min Range: -3.4028

Max Act: 3.3690. Min Act: -0.1700

Data Index: 3956105 (Open Web Text)

Max Activating Token Index: 393

Text #17

Max Range: 3.4028. Min Range: -3.4028

Max Act: 3.3454. Min Act: -0.1700

Data Index: 1583987 (Open Web Text)

Max Activating Token Index: 479

Text #18

Max Range: 3.4028. Min Range: -3.4028

Max Act: 3.3327. Min Act: -0.1700

Data Index: 5398741 (Open Web Text)

Max Activating Token Index: 276

Text #19

Max Range: 3.4028. Min Range: -3.4028

Max Act: 3.3350. Min Act: -0.1700

Data Index: 3556901 (Open Web Text)

Max Activating Token Index: 250