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

Dataset: Open Web Text

Neuron 18 in Layer 1

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: 1.6811. Min Range: -1.6811

Max Act: 1.6811. Min Act: -0.1700

Data Index: 7654824 (Open Web Text)

Max Activating Token Index: 825

Text #1

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.6732. Min Act: -0.1700

Data Index: 3547591 (Open Web Text)

Max Activating Token Index: 76

Text #2

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.6413. Min Act: -0.1700

Data Index: 7267114 (Open Web Text)

Max Activating Token Index: 573

Text #3

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.6409. Min Act: -0.1700

Data Index: 916925 (Open Web Text)

Max Activating Token Index: 703

Text #4

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.6210. Min Act: -0.1700

Data Index: 3499896 (Open Web Text)

Max Activating Token Index: 113

Text #5

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.6271. Min Act: -0.1700

Data Index: 2201850 (Open Web Text)

Max Activating Token Index: 584

Text #6

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.6286. Min Act: -0.1699

Data Index: 6238478 (Open Web Text)

Max Activating Token Index: 62

Text #7

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.6172. Min Act: -0.1700

Data Index: 2032256 (Open Web Text)

Max Activating Token Index: 974

Text #8

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.6227. Min Act: -0.1700

Data Index: 3059870 (Open Web Text)

Max Activating Token Index: 375

Text #9

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.6170. Min Act: -0.1700

Data Index: 1589802 (Open Web Text)

Max Activating Token Index: 891

Text #10

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.6210. Min Act: -0.1700

Data Index: 1393234 (Open Web Text)

Max Activating Token Index: 898

Text #11

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.6086. Min Act: -0.1699

Data Index: 1086528 (Open Web Text)

Max Activating Token Index: 603

Text #12

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.6078. Min Act: -0.1694

Data Index: 90897 (Open Web Text)

Max Activating Token Index: 910

Text #13

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.6064. Min Act: -0.1700

Data Index: 2528664 (Open Web Text)

Max Activating Token Index: 509

Text #14

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.6041. Min Act: -0.1699

Data Index: 4572062 (Open Web Text)

Max Activating Token Index: 113

Text #15

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.5982. Min Act: -0.1700

Data Index: 7938057 (Open Web Text)

Max Activating Token Index: 218

Text #16

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.6082. Min Act: -0.1700

Data Index: 2661865 (Open Web Text)

Max Activating Token Index: 487

Text #17

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.5954. Min Act: -0.1700

Data Index: 3983915 (Open Web Text)

Max Activating Token Index: 436

Text #18

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.6101. Min Act: -0.1700

Data Index: 7902593 (Open Web Text)

Max Activating Token Index: 928

Text #19

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.5986. Min Act: -0.1699

Data Index: 2717353 (Open Web Text)

Max Activating Token Index: 243