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

Dataset: Open Web Text

Neuron 429 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: 3.9621. Min Range: -3.9621

Max Act: 3.9621. Min Act: -0.1700

Data Index: 369046 (Open Web Text)

Max Activating Token Index: 459

Text #1

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.9259. Min Act: -0.1700

Data Index: 6142606 (Open Web Text)

Max Activating Token Index: 782

Text #2

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.8979. Min Act: -0.1700

Data Index: 4694251 (Open Web Text)

Max Activating Token Index: 109

Text #3

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.8604. Min Act: -0.1700

Data Index: 3726313 (Open Web Text)

Max Activating Token Index: 191

Text #4

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.8579. Min Act: -0.1700

Data Index: 1375423 (Open Web Text)

Max Activating Token Index: 595

Text #5

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.8703. Min Act: -0.1700

Data Index: 7452719 (Open Web Text)

Max Activating Token Index: 445

Text #6

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.8316. Min Act: -0.1700

Data Index: 2860325 (Open Web Text)

Max Activating Token Index: 887

Text #7

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.8027. Min Act: -0.1700

Data Index: 6855298 (Open Web Text)

Max Activating Token Index: 166

Text #8

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.8265. Min Act: -0.1700

Data Index: 7260224 (Open Web Text)

Max Activating Token Index: 227

Text #9

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.7920. Min Act: -0.1700

Data Index: 716182 (Open Web Text)

Max Activating Token Index: 746

Text #10

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.7927. Min Act: -0.1700

Data Index: 7462625 (Open Web Text)

Max Activating Token Index: 1004

Text #11

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.8148. Min Act: -0.1700

Data Index: 2963717 (Open Web Text)

Max Activating Token Index: 264

Text #12

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.7967. Min Act: -0.1700

Data Index: 1062594 (Open Web Text)

Max Activating Token Index: 423

Text #13

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.7791. Min Act: -0.1700

Data Index: 3682404 (Open Web Text)

Max Activating Token Index: 500

Text #14

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.7352. Min Act: -0.1700

Data Index: 3031049 (Open Web Text)

Max Activating Token Index: 625

Text #15

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.7605. Min Act: -0.1700

Data Index: 6311062 (Open Web Text)

Max Activating Token Index: 389

Text #16

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.7534. Min Act: -0.1700

Data Index: 6113551 (Open Web Text)

Max Activating Token Index: 81

Text #17

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.7404. Min Act: -0.1700

Data Index: 3489819 (Open Web Text)

Max Activating Token Index: 21

Text #18

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.7540. Min Act: -0.1700

Data Index: 5888232 (Open Web Text)

Max Activating Token Index: 872

Text #19

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.7616. Min Act: -0.1700

Data Index: 2616215 (Open Web Text)

Max Activating Token Index: 389