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

Dataset: Open Web Text

Neuron 1189 in Layer 3

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: 3.6876. Min Range: -3.6876

Max Act: 3.6658. Min Act: -0.1700

Data Index: 627123 (Open Web Text)

Max Activating Token Index: 547

Text #1

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.6876. Min Act: -0.1700

Data Index: 6592431 (Open Web Text)

Max Activating Token Index: 757

Text #2

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.6448. Min Act: -0.1700

Data Index: 957983 (Open Web Text)

Max Activating Token Index: 946

Text #3

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.5789. Min Act: -0.1700

Data Index: 8041792 (Open Web Text)

Max Activating Token Index: 386

Text #4

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.5651. Min Act: -0.1700

Data Index: 7667086 (Open Web Text)

Max Activating Token Index: 952

Text #5

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.5177. Min Act: -0.1700

Data Index: 12162 (Open Web Text)

Max Activating Token Index: 323

Text #6

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.5379. Min Act: -0.1700

Data Index: 3271020 (Open Web Text)

Max Activating Token Index: 501

Text #7

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.5195. Min Act: -0.1700

Data Index: 4210305 (Open Web Text)

Max Activating Token Index: 120

Text #8

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.5518. Min Act: -0.1700

Data Index: 8391832 (Open Web Text)

Max Activating Token Index: 891

Text #9

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.5294. Min Act: -0.1700

Data Index: 8372929 (Open Web Text)

Max Activating Token Index: 148

Text #10

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.5150. Min Act: -0.1700

Data Index: 1264882 (Open Web Text)

Max Activating Token Index: 711

Text #11

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.5122. Min Act: -0.1700

Data Index: 1388769 (Open Web Text)

Max Activating Token Index: 471

Text #12

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.5179. Min Act: -0.1700

Data Index: 3925507 (Open Web Text)

Max Activating Token Index: 233

Text #13

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.4870. Min Act: -0.1700

Data Index: 7063671 (Open Web Text)

Max Activating Token Index: 204

Text #14

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.4796. Min Act: -0.1700

Data Index: 5119423 (Open Web Text)

Max Activating Token Index: 459

Text #15

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.5112. Min Act: -0.1700

Data Index: 1795712 (Open Web Text)

Max Activating Token Index: 577

Text #16

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.4521. Min Act: -0.1700

Data Index: 2991948 (Open Web Text)

Max Activating Token Index: 1014

Text #17

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.4878. Min Act: -0.1700

Data Index: 6266589 (Open Web Text)

Max Activating Token Index: 633

Text #18

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.4498. Min Act: -0.1700

Data Index: 5201205 (Open Web Text)

Max Activating Token Index: 420

Text #19

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.4593. Min Act: -0.1700

Data Index: 300004 (Open Web Text)

Max Activating Token Index: 806