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

Dataset: Open Web Text

Neuron 1345 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: 1.5050. Min Range: -1.5050

Max Act: 1.5050. Min Act: -0.1700

Data Index: 6304605 (Open Web Text)

Max Activating Token Index: 31

Text #1

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.4767. Min Act: -0.1686

Data Index: 1726530 (Open Web Text)

Max Activating Token Index: 13

Text #2

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.4353. Min Act: -0.1700

Data Index: 1485518 (Open Web Text)

Max Activating Token Index: 596

Text #3

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.4194. Min Act: -0.1700

Data Index: 1107448 (Open Web Text)

Max Activating Token Index: 153

Text #4

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.4074. Min Act: -0.1700

Data Index: 8620230 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.4024. Min Act: -0.1699

Data Index: 3571123 (Open Web Text)

Max Activating Token Index: 584

Text #6

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.4041. Min Act: -0.1700

Data Index: 8513509 (Open Web Text)

Max Activating Token Index: 293

Text #7

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.3854. Min Act: -0.1700

Data Index: 498394 (Open Web Text)

Max Activating Token Index: 457

Text #8

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.3858. Min Act: -0.1700

Data Index: 1881614 (Open Web Text)

Max Activating Token Index: 156

Text #9

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.3833. Min Act: -0.1692

Data Index: 3518016 (Open Web Text)

Max Activating Token Index: 944

Text #10

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.3897. Min Act: -0.1700

Data Index: 363867 (Open Web Text)

Max Activating Token Index: 312

Text #11

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.3743. Min Act: -0.1698

Data Index: 7066976 (Open Web Text)

Max Activating Token Index: 658

Text #12

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.3710. Min Act: -0.1700

Data Index: 933008 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.3685. Min Act: -0.1699

Data Index: 3030013 (Open Web Text)

Max Activating Token Index: 910

Text #14

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.3727. Min Act: -0.1698

Data Index: 4592118 (Open Web Text)

Max Activating Token Index: 154

Text #15

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.3815. Min Act: -0.1700

Data Index: 7397837 (Open Web Text)

Max Activating Token Index: 287

Text #16

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.3665. Min Act: -0.1698

Data Index: 1726529 (Open Web Text)

Max Activating Token Index: 427

Text #17

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.3655. Min Act: -0.1700

Data Index: 5080291 (Open Web Text)

Max Activating Token Index: 437

Text #18

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.3522. Min Act: -0.1700

Data Index: 4561411 (Open Web Text)

Max Activating Token Index: 184

Text #19

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.3713. Min Act: -0.1696

Data Index: 5042982 (Open Web Text)

Max Activating Token Index: 617