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

Dataset: Open Web Text

Neuron 2740 in Layer 0

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: 3.0010. Min Range: -3.0010

Max Act: 3.0010. Min Act: -0.1700

Data Index: 3564100 (Open Web Text)

Max Activating Token Index: 33

Text #1

Max Range: 3.0010. Min Range: -3.0010

Max Act: 2.9666. Min Act: -0.1700

Data Index: 309338 (Open Web Text)

Max Activating Token Index: 191

Text #2

Max Range: 3.0010. Min Range: -3.0010

Max Act: 2.8896. Min Act: -0.1700

Data Index: 3497670 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.0010. Min Range: -3.0010

Max Act: 2.8745. Min Act: -0.1700

Data Index: 2283727 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.0010. Min Range: -3.0010

Max Act: 2.8689. Min Act: -0.1700

Data Index: 1136748 (Open Web Text)

Max Activating Token Index: 129

Text #5

Max Range: 3.0010. Min Range: -3.0010

Max Act: 2.8596. Min Act: -0.1700

Data Index: 8694130 (Open Web Text)

Max Activating Token Index: 900

Text #6

Max Range: 3.0010. Min Range: -3.0010

Max Act: 2.8514. Min Act: -0.1700

Data Index: 5937182 (Open Web Text)

Max Activating Token Index: 520

Text #7

Max Range: 3.0010. Min Range: -3.0010

Max Act: 2.8375. Min Act: -0.1700

Data Index: 7712854 (Open Web Text)

Max Activating Token Index: 908

Text #8

Max Range: 3.0010. Min Range: -3.0010

Max Act: 2.8389. Min Act: -0.1700

Data Index: 6063118 (Open Web Text)

Max Activating Token Index: 97

Text #9

Max Range: 3.0010. Min Range: -3.0010

Max Act: 2.8357. Min Act: -0.1700

Data Index: 1203502 (Open Web Text)

Max Activating Token Index: 392

Text #10

Max Range: 3.0010. Min Range: -3.0010

Max Act: 2.8297. Min Act: -0.1700

Data Index: 4768516 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.0010. Min Range: -3.0010

Max Act: 2.8140. Min Act: -0.1700

Data Index: 4904442 (Open Web Text)

Max Activating Token Index: 718

Text #12

Max Range: 3.0010. Min Range: -3.0010

Max Act: 2.8077. Min Act: -0.1700

Data Index: 7015257 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.0010. Min Range: -3.0010

Max Act: 2.8242. Min Act: -0.1700

Data Index: 8517972 (Open Web Text)

Max Activating Token Index: 678

Text #14

Max Range: 3.0010. Min Range: -3.0010

Max Act: 2.8031. Min Act: -0.1700

Data Index: 3056207 (Open Web Text)

Max Activating Token Index: 659

Text #15

Max Range: 3.0010. Min Range: -3.0010

Max Act: 2.8156. Min Act: -0.1700

Data Index: 4746156 (Open Web Text)

Max Activating Token Index: 37

Text #16

Max Range: 3.0010. Min Range: -3.0010

Max Act: 2.8116. Min Act: -0.1700

Data Index: 8698374 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.0010. Min Range: -3.0010

Max Act: 2.8180. Min Act: -0.1700

Data Index: 3125953 (Open Web Text)

Max Activating Token Index: 58

Text #18

Max Range: 3.0010. Min Range: -3.0010

Max Act: 2.8194. Min Act: -0.1700

Data Index: 2347380 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.0010. Min Range: -3.0010

Max Act: 2.7956. Min Act: -0.1700

Data Index: 3465086 (Open Web Text)

Max Activating Token Index: 671