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

Dataset: Open Web Text

Neuron 59 in Layer 6

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: 4.4735. Min Range: -4.4735

Max Act: 4.4735. Min Act: -0.1700

Data Index: 214039 (Open Web Text)

Max Activating Token Index: 211

Text #1

Max Range: 4.4735. Min Range: -4.4735

Max Act: 4.4563. Min Act: -0.1700

Data Index: 1491830 (Open Web Text)

Max Activating Token Index: 369

Text #2

Max Range: 4.4735. Min Range: -4.4735

Max Act: 4.4401. Min Act: -0.1700

Data Index: 6192662 (Open Web Text)

Max Activating Token Index: 884

Text #3

Max Range: 4.4735. Min Range: -4.4735

Max Act: 4.3531. Min Act: -0.1700

Data Index: 7526925 (Open Web Text)

Max Activating Token Index: 233

Text #4

Max Range: 4.4735. Min Range: -4.4735

Max Act: 4.2928. Min Act: -0.1700

Data Index: 7018568 (Open Web Text)

Max Activating Token Index: 717

Text #5

Max Range: 4.4735. Min Range: -4.4735

Max Act: 4.2919. Min Act: -0.1700

Data Index: 4821922 (Open Web Text)

Max Activating Token Index: 679

Text #6

Max Range: 4.4735. Min Range: -4.4735

Max Act: 4.1368. Min Act: -0.1700

Data Index: 1882685 (Open Web Text)

Max Activating Token Index: 759

Text #7

Max Range: 4.4735. Min Range: -4.4735

Max Act: 4.1822. Min Act: -0.1700

Data Index: 287876 (Open Web Text)

Max Activating Token Index: 408

Text #8

Max Range: 4.4735. Min Range: -4.4735

Max Act: 4.1181. Min Act: -0.1700

Data Index: 6850052 (Open Web Text)

Max Activating Token Index: 873

Text #9

Max Range: 4.4735. Min Range: -4.4735

Max Act: 4.1051. Min Act: -0.1700

Data Index: 6250467 (Open Web Text)

Max Activating Token Index: 652

Text #10

Max Range: 4.4735. Min Range: -4.4735

Max Act: 4.0729. Min Act: -0.1700

Data Index: 3201720 (Open Web Text)

Max Activating Token Index: 423

Text #11

Max Range: 4.4735. Min Range: -4.4735

Max Act: 4.1250. Min Act: -0.1700

Data Index: 1805906 (Open Web Text)

Max Activating Token Index: 704

Text #12

Max Range: 4.4735. Min Range: -4.4735

Max Act: 4.0713. Min Act: -0.1700

Data Index: 6780045 (Open Web Text)

Max Activating Token Index: 620

Text #13

Max Range: 4.4735. Min Range: -4.4735

Max Act: 4.0846. Min Act: -0.1700

Data Index: 8184572 (Open Web Text)

Max Activating Token Index: 794

Text #14

Max Range: 4.4735. Min Range: -4.4735

Max Act: 4.0827. Min Act: -0.1700

Data Index: 3090918 (Open Web Text)

Max Activating Token Index: 516

Text #15

Max Range: 4.4735. Min Range: -4.4735

Max Act: 4.1245. Min Act: -0.1700

Data Index: 2764332 (Open Web Text)

Max Activating Token Index: 937

Text #16

Max Range: 4.4735. Min Range: -4.4735

Max Act: 4.0595. Min Act: -0.1700

Data Index: 279261 (Open Web Text)

Max Activating Token Index: 975

Text #17

Max Range: 4.4735. Min Range: -4.4735

Max Act: 4.0175. Min Act: -0.1700

Data Index: 5202071 (Open Web Text)

Max Activating Token Index: 720

Text #18

Max Range: 4.4735. Min Range: -4.4735

Max Act: 3.9999. Min Act: -0.1700

Data Index: 1944458 (Open Web Text)

Max Activating Token Index: 806

Text #19

Max Range: 4.4735. Min Range: -4.4735

Max Act: 3.9967. Min Act: -0.1700

Data Index: 3505046 (Open Web Text)

Max Activating Token Index: 899