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

Dataset: Open Web Text

Neuron 1899 in Layer 3

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: 2.9810. Min Range: -2.9810

Max Act: 2.9810. Min Act: -0.1700

Data Index: 6033181 (Open Web Text)

Max Activating Token Index: 1009

Text #1

Max Range: 2.9810. Min Range: -2.9810

Max Act: 2.8908. Min Act: -0.1700

Data Index: 3454545 (Open Web Text)

Max Activating Token Index: 1021

Text #2

Max Range: 2.9810. Min Range: -2.9810

Max Act: 2.8419. Min Act: -0.1700

Data Index: 4305462 (Open Web Text)

Max Activating Token Index: 362

Text #3

Max Range: 2.9810. Min Range: -2.9810

Max Act: 2.8086. Min Act: -0.1700

Data Index: 2276973 (Open Web Text)

Max Activating Token Index: 309

Text #4

Max Range: 2.9810. Min Range: -2.9810

Max Act: 2.8253. Min Act: -0.1700

Data Index: 7184304 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 2.9810. Min Range: -2.9810

Max Act: 2.8115. Min Act: -0.1700

Data Index: 3095408 (Open Web Text)

Max Activating Token Index: 902

Text #6

Max Range: 2.9810. Min Range: -2.9810

Max Act: 2.7682. Min Act: -0.1700

Data Index: 4398603 (Open Web Text)

Max Activating Token Index: 837

Text #7

Max Range: 2.9810. Min Range: -2.9810

Max Act: 2.7791. Min Act: -0.1700

Data Index: 322235 (Open Web Text)

Max Activating Token Index: 215

Text #8

Max Range: 2.9810. Min Range: -2.9810

Max Act: 2.7769. Min Act: -0.1700

Data Index: 6331523 (Open Web Text)

Max Activating Token Index: 431

Text #9

Max Range: 2.9810. Min Range: -2.9810

Max Act: 2.7359. Min Act: -0.1700

Data Index: 4593067 (Open Web Text)

Max Activating Token Index: 1007

Text #10

Max Range: 2.9810. Min Range: -2.9810

Max Act: 2.7583. Min Act: -0.1700

Data Index: 688986 (Open Web Text)

Max Activating Token Index: 526

Text #11

Max Range: 2.9810. Min Range: -2.9810

Max Act: 2.7752. Min Act: -0.1700

Data Index: 5039622 (Open Web Text)

Max Activating Token Index: 966

Text #12

Max Range: 2.9810. Min Range: -2.9810

Max Act: 2.7580. Min Act: -0.1700

Data Index: 92773 (Open Web Text)

Max Activating Token Index: 753

Text #13

Max Range: 2.9810. Min Range: -2.9810

Max Act: 2.7651. Min Act: -0.1700

Data Index: 6878767 (Open Web Text)

Max Activating Token Index: 1017

Text #14

Max Range: 2.9810. Min Range: -2.9810

Max Act: 2.7674. Min Act: -0.1700

Data Index: 4398605 (Open Web Text)

Max Activating Token Index: 489

Text #15

Max Range: 2.9810. Min Range: -2.9810

Max Act: 2.7355. Min Act: -0.1700

Data Index: 3973790 (Open Web Text)

Max Activating Token Index: 689

Text #16

Max Range: 2.9810. Min Range: -2.9810

Max Act: 2.7526. Min Act: -0.1700

Data Index: 8597093 (Open Web Text)

Max Activating Token Index: 30

Text #17

Max Range: 2.9810. Min Range: -2.9810

Max Act: 2.7446. Min Act: -0.1700

Data Index: 3617547 (Open Web Text)

Max Activating Token Index: 653

Text #18

Max Range: 2.9810. Min Range: -2.9810

Max Act: 2.7618. Min Act: -0.1700

Data Index: 6945982 (Open Web Text)

Max Activating Token Index: 820

Text #19

Max Range: 2.9810. Min Range: -2.9810

Max Act: 2.7381. Min Act: -0.1700

Data Index: 829131 (Open Web Text)

Max Activating Token Index: 976