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

Dataset: Open Web Text

Neuron 70 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: 3.7065. Min Range: -3.7065

Max Act: 3.7065. Min Act: -0.1700

Data Index: 1865189 (Open Web Text)

Max Activating Token Index: 209

Text #1

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.6491. Min Act: -0.1700

Data Index: 7034865 (Open Web Text)

Max Activating Token Index: 656

Text #2

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.5891. Min Act: -0.1700

Data Index: 8638602 (Open Web Text)

Max Activating Token Index: 253

Text #3

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.5499. Min Act: -0.1700

Data Index: 4886158 (Open Web Text)

Max Activating Token Index: 329

Text #4

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.5177. Min Act: -0.1700

Data Index: 3510549 (Open Web Text)

Max Activating Token Index: 186

Text #5

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.5187. Min Act: -0.1700

Data Index: 4732491 (Open Web Text)

Max Activating Token Index: 974

Text #6

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.5116. Min Act: -0.1700

Data Index: 7750038 (Open Web Text)

Max Activating Token Index: 834

Text #7

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.4984. Min Act: -0.1700

Data Index: 7440894 (Open Web Text)

Max Activating Token Index: 344

Text #8

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.5111. Min Act: -0.1700

Data Index: 8723882 (Open Web Text)

Max Activating Token Index: 121

Text #9

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.4802. Min Act: -0.1700

Data Index: 4691615 (Open Web Text)

Max Activating Token Index: 83

Text #10

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.4980. Min Act: -0.1700

Data Index: 1575461 (Open Web Text)

Max Activating Token Index: 653

Text #11

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.4777. Min Act: -0.1700

Data Index: 8126017 (Open Web Text)

Max Activating Token Index: 694

Text #12

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.4762. Min Act: -0.1700

Data Index: 1638625 (Open Web Text)

Max Activating Token Index: 746

Text #13

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.4834. Min Act: -0.1700

Data Index: 5929117 (Open Web Text)

Max Activating Token Index: 949

Text #14

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.4805. Min Act: -0.1700

Data Index: 3955214 (Open Web Text)

Max Activating Token Index: 578

Text #15

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.4660. Min Act: -0.1700

Data Index: 8079487 (Open Web Text)

Max Activating Token Index: 717

Text #16

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.4822. Min Act: -0.1700

Data Index: 7247950 (Open Web Text)

Max Activating Token Index: 288

Text #17

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.4884. Min Act: -0.1700

Data Index: 6054472 (Open Web Text)

Max Activating Token Index: 228

Text #18

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.4701. Min Act: -0.1700

Data Index: 1532169 (Open Web Text)

Max Activating Token Index: 639

Text #19

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.4656. Min Act: -0.1700

Data Index: 813526 (Open Web Text)

Max Activating Token Index: 644