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

Dataset: Open Web Text

Neuron 2554 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: 3.1347. Min Range: -3.1347

Max Act: 3.1347. Min Act: -0.1700

Data Index: 7609344 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.1347. Min Range: -3.1347

Max Act: 3.0934. Min Act: -0.1700

Data Index: 2115425 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 3.1347. Min Range: -3.1347

Max Act: 3.0899. Min Act: -0.1700

Data Index: 6718740 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.9975. Min Act: -0.1700

Data Index: 3250914 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.9741. Min Act: -0.1700

Data Index: 3292051 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.9175. Min Act: -0.1700

Data Index: 8225461 (Open Web Text)

Max Activating Token Index: 573

Text #6

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.9405. Min Act: -0.1700

Data Index: 692821 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.9049. Min Act: -0.1700

Data Index: 314897 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.8828. Min Act: -0.1700

Data Index: 3724230 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.8969. Min Act: -0.1700

Data Index: 3898233 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.9068. Min Act: -0.1700

Data Index: 8177155 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.8043. Min Act: -0.1700

Data Index: 4539050 (Open Web Text)

Max Activating Token Index: 865

Text #12

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.8432. Min Act: -0.1700

Data Index: 7741791 (Open Web Text)

Max Activating Token Index: 603

Text #13

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.8485. Min Act: -0.1700

Data Index: 1558856 (Open Web Text)

Max Activating Token Index: 386

Text #14

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.8840. Min Act: -0.1700

Data Index: 3465268 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.9148. Min Act: -0.1700

Data Index: 3426568 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.8131. Min Act: -0.1700

Data Index: 1794166 (Open Web Text)

Max Activating Token Index: 134

Text #17

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.8452. Min Act: -0.1700

Data Index: 3633900 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.8726. Min Act: -0.1700

Data Index: 2932585 (Open Web Text)

Max Activating Token Index: 493

Text #19

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.8441. Min Act: -0.1700

Data Index: 2539124 (Open Web Text)

Max Activating Token Index: 1023