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

Dataset: Open Web Text

Neuron 1603 in Layer 6

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: 3.1041. Min Range: -3.1041

Max Act: 3.0972. Min Act: -0.1700

Data Index: 8140215 (Open Web Text)

Max Activating Token Index: 958

Text #1

Max Range: 3.1041. Min Range: -3.1041

Max Act: 3.1041. Min Act: -0.1700

Data Index: 8140230 (Open Web Text)

Max Activating Token Index: 584

Text #2

Max Range: 3.1041. Min Range: -3.1041

Max Act: 3.0989. Min Act: -0.1700

Data Index: 3928470 (Open Web Text)

Max Activating Token Index: 867

Text #3

Max Range: 3.1041. Min Range: -3.1041

Max Act: 3.0764. Min Act: -0.1700

Data Index: 8140225 (Open Web Text)

Max Activating Token Index: 524

Text #4

Max Range: 3.1041. Min Range: -3.1041

Max Act: 3.0767. Min Act: -0.1700

Data Index: 8379241 (Open Web Text)

Max Activating Token Index: 263

Text #5

Max Range: 3.1041. Min Range: -3.1041

Max Act: 3.0640. Min Act: -0.1700

Data Index: 840373 (Open Web Text)

Max Activating Token Index: 923

Text #6

Max Range: 3.1041. Min Range: -3.1041

Max Act: 3.0013. Min Act: -0.1700

Data Index: 6134224 (Open Web Text)

Max Activating Token Index: 766

Text #7

Max Range: 3.1041. Min Range: -3.1041

Max Act: 2.9948. Min Act: -0.1700

Data Index: 8140214 (Open Web Text)

Max Activating Token Index: 756

Text #8

Max Range: 3.1041. Min Range: -3.1041

Max Act: 2.9689. Min Act: -0.1700

Data Index: 8140226 (Open Web Text)

Max Activating Token Index: 407

Text #9

Max Range: 3.1041. Min Range: -3.1041

Max Act: 2.9497. Min Act: -0.1700

Data Index: 1162117 (Open Web Text)

Max Activating Token Index: 944

Text #10

Max Range: 3.1041. Min Range: -3.1041

Max Act: 2.9667. Min Act: -0.1700

Data Index: 6668650 (Open Web Text)

Max Activating Token Index: 321

Text #11

Max Range: 3.1041. Min Range: -3.1041

Max Act: 2.9235. Min Act: -0.1700

Data Index: 8140223 (Open Web Text)

Max Activating Token Index: 597

Text #12

Max Range: 3.1041. Min Range: -3.1041

Max Act: 2.9513. Min Act: -0.1700

Data Index: 8140236 (Open Web Text)

Max Activating Token Index: 849

Text #13

Max Range: 3.1041. Min Range: -3.1041

Max Act: 2.9212. Min Act: -0.1700

Data Index: 8140220 (Open Web Text)

Max Activating Token Index: 702

Text #14

Max Range: 3.1041. Min Range: -3.1041

Max Act: 2.9359. Min Act: -0.1700

Data Index: 8140221 (Open Web Text)

Max Activating Token Index: 539

Text #15

Max Range: 3.1041. Min Range: -3.1041

Max Act: 2.9174. Min Act: -0.1700

Data Index: 5591292 (Open Web Text)

Max Activating Token Index: 708

Text #16

Max Range: 3.1041. Min Range: -3.1041

Max Act: 2.8903. Min Act: -0.1700

Data Index: 5053849 (Open Web Text)

Max Activating Token Index: 996

Text #17

Max Range: 3.1041. Min Range: -3.1041

Max Act: 2.8638. Min Act: -0.1700

Data Index: 8161671 (Open Web Text)

Max Activating Token Index: 523

Text #18

Max Range: 3.1041. Min Range: -3.1041

Max Act: 2.8991. Min Act: -0.1700

Data Index: 8140213 (Open Web Text)

Max Activating Token Index: 926

Text #19

Max Range: 3.1041. Min Range: -3.1041

Max Act: 2.8781. Min Act: -0.1700

Data Index: 3779004 (Open Web Text)

Max Activating Token Index: 562