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

Dataset: Open Web Text

Neuron 508 in Layer 4

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: 5.8163. Min Range: -5.8163

Max Act: 5.8163. Min Act: -0.1700

Data Index: 3496998 (Open Web Text)

Max Activating Token Index: 510

Text #1

Max Range: 5.8163. Min Range: -5.8163

Max Act: 5.7129. Min Act: -0.1700

Data Index: 1942429 (Open Web Text)

Max Activating Token Index: 678

Text #2

Max Range: 5.8163. Min Range: -5.8163

Max Act: 5.5123. Min Act: -0.1700

Data Index: 7282541 (Open Web Text)

Max Activating Token Index: 649

Text #3

Max Range: 5.8163. Min Range: -5.8163

Max Act: 5.5145. Min Act: -0.1700

Data Index: 5983066 (Open Web Text)

Max Activating Token Index: 101

Text #4

Max Range: 5.8163. Min Range: -5.8163

Max Act: 5.4454. Min Act: -0.1700

Data Index: 4807290 (Open Web Text)

Max Activating Token Index: 761

Text #5

Max Range: 5.8163. Min Range: -5.8163

Max Act: 5.5371. Min Act: -0.1700

Data Index: 5690866 (Open Web Text)

Max Activating Token Index: 719

Text #6

Max Range: 5.8163. Min Range: -5.8163

Max Act: 5.5168. Min Act: -0.1700

Data Index: 3245899 (Open Web Text)

Max Activating Token Index: 1016

Text #7

Max Range: 5.8163. Min Range: -5.8163

Max Act: 5.4478. Min Act: -0.1700

Data Index: 811226 (Open Web Text)

Max Activating Token Index: 72

Text #8

Max Range: 5.8163. Min Range: -5.8163

Max Act: 5.4686. Min Act: -0.1700

Data Index: 3912563 (Open Web Text)

Max Activating Token Index: 294

Text #9

Max Range: 5.8163. Min Range: -5.8163

Max Act: 5.4791. Min Act: -0.1700

Data Index: 8767836 (Open Web Text)

Max Activating Token Index: 492

Text #10

Max Range: 5.8163. Min Range: -5.8163

Max Act: 5.4578. Min Act: -0.1700

Data Index: 6671946 (Open Web Text)

Max Activating Token Index: 512

Text #11

Max Range: 5.8163. Min Range: -5.8163

Max Act: 5.4154. Min Act: -0.1700

Data Index: 8461912 (Open Web Text)

Max Activating Token Index: 416

Text #12

Max Range: 5.8163. Min Range: -5.8163

Max Act: 5.4121. Min Act: -0.1700

Data Index: 6513238 (Open Web Text)

Max Activating Token Index: 554

Text #13

Max Range: 5.8163. Min Range: -5.8163

Max Act: 5.3978. Min Act: -0.1700

Data Index: 7166794 (Open Web Text)

Max Activating Token Index: 624

Text #14

Max Range: 5.8163. Min Range: -5.8163

Max Act: 5.3061. Min Act: -0.1700

Data Index: 4298172 (Open Web Text)

Max Activating Token Index: 811

Text #15

Max Range: 5.8163. Min Range: -5.8163

Max Act: 5.4049. Min Act: -0.1700

Data Index: 6207412 (Open Web Text)

Max Activating Token Index: 626

Text #16

Max Range: 5.8163. Min Range: -5.8163

Max Act: 5.3652. Min Act: -0.1700

Data Index: 5564588 (Open Web Text)

Max Activating Token Index: 763

Text #17

Max Range: 5.8163. Min Range: -5.8163

Max Act: 5.3960. Min Act: -0.1700

Data Index: 1755100 (Open Web Text)

Max Activating Token Index: 376

Text #18

Max Range: 5.8163. Min Range: -5.8163

Max Act: 5.4282. Min Act: -0.1700

Data Index: 5897186 (Open Web Text)

Max Activating Token Index: 807

Text #19

Max Range: 5.8163. Min Range: -5.8163

Max Act: 5.3514. Min Act: -0.1700

Data Index: 2672002 (Open Web Text)

Max Activating Token Index: 544