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

Dataset: Open Web Text

Neuron 2787 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: 1.7117. Min Range: -1.7117

Max Act: 1.7117. Min Act: -0.1700

Data Index: 2111439 (Open Web Text)

Max Activating Token Index: 18

Text #1

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.7051. Min Act: -0.1700

Data Index: 5601546 (Open Web Text)

Max Activating Token Index: 14

Text #2

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.6741. Min Act: -0.1700

Data Index: 3727003 (Open Web Text)

Max Activating Token Index: 14

Text #3

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.6730. Min Act: -0.1700

Data Index: 3418294 (Open Web Text)

Max Activating Token Index: 143

Text #4

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.6677. Min Act: -0.1699

Data Index: 7018136 (Open Web Text)

Max Activating Token Index: 985

Text #5

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.6776. Min Act: -0.1700

Data Index: 5195297 (Open Web Text)

Max Activating Token Index: 254

Text #6

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.6768. Min Act: -0.1700

Data Index: 6880748 (Open Web Text)

Max Activating Token Index: 28

Text #7

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.6670. Min Act: -0.1700

Data Index: 3155725 (Open Web Text)

Max Activating Token Index: 133

Text #8

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.6576. Min Act: -0.1700

Data Index: 3229862 (Open Web Text)

Max Activating Token Index: 227

Text #9

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.6645. Min Act: -0.1700

Data Index: 74162 (Open Web Text)

Max Activating Token Index: 887

Text #10

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.6559. Min Act: -0.1700

Data Index: 8452143 (Open Web Text)

Max Activating Token Index: 382

Text #11

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.6537. Min Act: -0.1700

Data Index: 4800062 (Open Web Text)

Max Activating Token Index: 529

Text #12

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.6502. Min Act: -0.1700

Data Index: 2548696 (Open Web Text)

Max Activating Token Index: 431

Text #13

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.6490. Min Act: -0.1700

Data Index: 1654569 (Open Web Text)

Max Activating Token Index: 288

Text #14

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.6551. Min Act: -0.1700

Data Index: 6167647 (Open Web Text)

Max Activating Token Index: 42

Text #15

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.6434. Min Act: -0.1700

Data Index: 6770615 (Open Web Text)

Max Activating Token Index: 377

Text #16

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.6360. Min Act: -0.1700

Data Index: 7664100 (Open Web Text)

Max Activating Token Index: 21

Text #17

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.6402. Min Act: -0.1700

Data Index: 6664995 (Open Web Text)

Max Activating Token Index: 24

Text #18

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.6448. Min Act: -0.1700

Data Index: 7714598 (Open Web Text)

Max Activating Token Index: 245

Text #19

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.6363. Min Act: -0.1700

Data Index: 2346547 (Open Web Text)

Max Activating Token Index: 22