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

Dataset: Open Web Text

Neuron 1497 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: 4.3854. Min Range: -4.3854

Max Act: 4.3854. Min Act: -0.1700

Data Index: 8430383 (Open Web Text)

Max Activating Token Index: 838

Text #1

Max Range: 4.3854. Min Range: -4.3854

Max Act: 4.3801. Min Act: -0.1700

Data Index: 7376594 (Open Web Text)

Max Activating Token Index: 509

Text #2

Max Range: 4.3854. Min Range: -4.3854

Max Act: 4.3074. Min Act: -0.1700

Data Index: 1054630 (Open Web Text)

Max Activating Token Index: 307

Text #3

Max Range: 4.3854. Min Range: -4.3854

Max Act: 4.2811. Min Act: -0.1700

Data Index: 4888669 (Open Web Text)

Max Activating Token Index: 903

Text #4

Max Range: 4.3854. Min Range: -4.3854

Max Act: 4.2841. Min Act: -0.1700

Data Index: 7576969 (Open Web Text)

Max Activating Token Index: 550

Text #5

Max Range: 4.3854. Min Range: -4.3854

Max Act: 4.2444. Min Act: -0.1700

Data Index: 7939689 (Open Web Text)

Max Activating Token Index: 439

Text #6

Max Range: 4.3854. Min Range: -4.3854

Max Act: 4.2306. Min Act: -0.1700

Data Index: 765489 (Open Web Text)

Max Activating Token Index: 858

Text #7

Max Range: 4.3854. Min Range: -4.3854

Max Act: 4.2365. Min Act: -0.1700

Data Index: 4133816 (Open Web Text)

Max Activating Token Index: 712

Text #8

Max Range: 4.3854. Min Range: -4.3854

Max Act: 4.2060. Min Act: -0.1700

Data Index: 279089 (Open Web Text)

Max Activating Token Index: 837

Text #9

Max Range: 4.3854. Min Range: -4.3854

Max Act: 4.1981. Min Act: -0.1700

Data Index: 8600810 (Open Web Text)

Max Activating Token Index: 324

Text #10

Max Range: 4.3854. Min Range: -4.3854

Max Act: 4.2128. Min Act: -0.1700

Data Index: 2990701 (Open Web Text)

Max Activating Token Index: 96

Text #11

Max Range: 4.3854. Min Range: -4.3854

Max Act: 4.2073. Min Act: -0.1700

Data Index: 6619829 (Open Web Text)

Max Activating Token Index: 724

Text #12

Max Range: 4.3854. Min Range: -4.3854

Max Act: 4.2131. Min Act: -0.1700

Data Index: 6831599 (Open Web Text)

Max Activating Token Index: 476

Text #13

Max Range: 4.3854. Min Range: -4.3854

Max Act: 4.1894. Min Act: -0.1700

Data Index: 5468919 (Open Web Text)

Max Activating Token Index: 665

Text #14

Max Range: 4.3854. Min Range: -4.3854

Max Act: 4.1699. Min Act: -0.1700

Data Index: 5617800 (Open Web Text)

Max Activating Token Index: 101

Text #15

Max Range: 4.3854. Min Range: -4.3854

Max Act: 4.1907. Min Act: -0.1700

Data Index: 6935601 (Open Web Text)

Max Activating Token Index: 651

Text #16

Max Range: 4.3854. Min Range: -4.3854

Max Act: 4.1854. Min Act: -0.1700

Data Index: 6081458 (Open Web Text)

Max Activating Token Index: 314

Text #17

Max Range: 4.3854. Min Range: -4.3854

Max Act: 4.1805. Min Act: -0.1700

Data Index: 1890367 (Open Web Text)

Max Activating Token Index: 476

Text #18

Max Range: 4.3854. Min Range: -4.3854

Max Act: 4.1603. Min Act: -0.1700

Data Index: 1429919 (Open Web Text)

Max Activating Token Index: 707

Text #19

Max Range: 4.3854. Min Range: -4.3854

Max Act: 4.1428. Min Act: -0.1700

Data Index: 4250206 (Open Web Text)

Max Activating Token Index: 1022