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

Dataset: Open Web Text

Neuron 1910 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: 3.3044. Min Range: -3.3044

Max Act: 3.3044. Min Act: -0.1700

Data Index: 1184319 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.3044. Min Range: -3.3044

Max Act: 3.1768. Min Act: -0.1700

Data Index: 2391030 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 3.3044. Min Range: -3.3044

Max Act: 3.1173. Min Act: -0.1700

Data Index: 6121159 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 3.3044. Min Range: -3.3044

Max Act: 3.0678. Min Act: -0.1700

Data Index: 6923634 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 3.3044. Min Range: -3.3044

Max Act: 3.0010. Min Act: -0.1700

Data Index: 2113934 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 3.3044. Min Range: -3.3044

Max Act: 3.0542. Min Act: -0.1700

Data Index: 7237126 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 3.3044. Min Range: -3.3044

Max Act: 3.0322. Min Act: -0.1700

Data Index: 8634856 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 3.3044. Min Range: -3.3044

Max Act: 3.0019. Min Act: -0.1700

Data Index: 2437591 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 3.3044. Min Range: -3.3044

Max Act: 2.9215. Min Act: -0.1700

Data Index: 2006205 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 3.3044. Min Range: -3.3044

Max Act: 2.9842. Min Act: -0.1700

Data Index: 7266653 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 3.3044. Min Range: -3.3044

Max Act: 2.9171. Min Act: -0.1700

Data Index: 2915392 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 3.3044. Min Range: -3.3044

Max Act: 2.8887. Min Act: -0.1700

Data Index: 7556461 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 3.3044. Min Range: -3.3044

Max Act: 2.8832. Min Act: -0.1700

Data Index: 7614204 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 3.3044. Min Range: -3.3044

Max Act: 2.9391. Min Act: -0.1700

Data Index: 723123 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 3.3044. Min Range: -3.3044

Max Act: 2.9359. Min Act: -0.1700

Data Index: 7804884 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 3.3044. Min Range: -3.3044

Max Act: 2.9223. Min Act: -0.1700

Data Index: 5283042 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 3.3044. Min Range: -3.3044

Max Act: 2.8879. Min Act: -0.1700

Data Index: 6089471 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 3.3044. Min Range: -3.3044

Max Act: 2.8771. Min Act: -0.1700

Data Index: 4066344 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 3.3044. Min Range: -3.3044

Max Act: 2.8522. Min Act: -0.1700

Data Index: 698732 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 3.3044. Min Range: -3.3044

Max Act: 2.8341. Min Act: -0.1700

Data Index: 3143967 (Open Web Text)

Max Activating Token Index: 1023