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

Dataset: Open Web Text

Neuron 657 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: 1.5872. Min Range: -1.5872

Max Act: 1.5872. Min Act: -0.1700

Data Index: 4868535 (Open Web Text)

Max Activating Token Index: 145

Text #1

Max Range: 1.5872. Min Range: -1.5872

Max Act: 1.5558. Min Act: -0.1700

Data Index: 1114432 (Open Web Text)

Max Activating Token Index: 994

Text #2

Max Range: 1.5872. Min Range: -1.5872

Max Act: 1.5446. Min Act: -0.1700

Data Index: 173755 (Open Web Text)

Max Activating Token Index: 772

Text #3

Max Range: 1.5872. Min Range: -1.5872

Max Act: 1.5188. Min Act: -0.1700

Data Index: 977748 (Open Web Text)

Max Activating Token Index: 657

Text #4

Max Range: 1.5872. Min Range: -1.5872

Max Act: 1.5148. Min Act: -0.1700

Data Index: 6355284 (Open Web Text)

Max Activating Token Index: 981

Text #5

Max Range: 1.5872. Min Range: -1.5872

Max Act: 1.4939. Min Act: -0.1700

Data Index: 6735106 (Open Web Text)

Max Activating Token Index: 533

Text #6

Max Range: 1.5872. Min Range: -1.5872

Max Act: 1.4933. Min Act: -0.1700

Data Index: 4478161 (Open Web Text)

Max Activating Token Index: 207

Text #7

Max Range: 1.5872. Min Range: -1.5872

Max Act: 1.4940. Min Act: -0.1700

Data Index: 1216456 (Open Web Text)

Max Activating Token Index: 987

Text #8

Max Range: 1.5872. Min Range: -1.5872

Max Act: 1.4843. Min Act: -0.1700

Data Index: 3874693 (Open Web Text)

Max Activating Token Index: 959

Text #9

Max Range: 1.5872. Min Range: -1.5872

Max Act: 1.4814. Min Act: -0.1700

Data Index: 1416136 (Open Web Text)

Max Activating Token Index: 550

Text #10

Max Range: 1.5872. Min Range: -1.5872

Max Act: 1.4923. Min Act: -0.1700

Data Index: 1060466 (Open Web Text)

Max Activating Token Index: 992

Text #11

Max Range: 1.5872. Min Range: -1.5872

Max Act: 1.4693. Min Act: -0.1700

Data Index: 4915669 (Open Web Text)

Max Activating Token Index: 217

Text #12

Max Range: 1.5872. Min Range: -1.5872

Max Act: 1.4658. Min Act: -0.1700

Data Index: 5095258 (Open Web Text)

Max Activating Token Index: 701

Text #13

Max Range: 1.5872. Min Range: -1.5872

Max Act: 1.4594. Min Act: -0.1700

Data Index: 4393527 (Open Web Text)

Max Activating Token Index: 694

Text #14

Max Range: 1.5872. Min Range: -1.5872

Max Act: 1.4667. Min Act: -0.1700

Data Index: 1706682 (Open Web Text)

Max Activating Token Index: 424

Text #15

Max Range: 1.5872. Min Range: -1.5872

Max Act: 1.4598. Min Act: -0.1700

Data Index: 759512 (Open Web Text)

Max Activating Token Index: 494

Text #16

Max Range: 1.5872. Min Range: -1.5872

Max Act: 1.4718. Min Act: -0.1700

Data Index: 4556656 (Open Web Text)

Max Activating Token Index: 303

Text #17

Max Range: 1.5872. Min Range: -1.5872

Max Act: 1.4672. Min Act: -0.1700

Data Index: 5772952 (Open Web Text)

Max Activating Token Index: 729

Text #18

Max Range: 1.5872. Min Range: -1.5872

Max Act: 1.4688. Min Act: -0.1700

Data Index: 4565990 (Open Web Text)

Max Activating Token Index: 265

Text #19

Max Range: 1.5872. Min Range: -1.5872

Max Act: 1.4727. Min Act: -0.1700

Data Index: 5971633 (Open Web Text)

Max Activating Token Index: 805