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

Dataset: Open Web Text

Neuron 133 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: 3.0881. Min Range: -3.0881

Max Act: 3.0881. Min Act: -0.1700

Data Index: 2948160 (Open Web Text)

Max Activating Token Index: 391

Text #1

Max Range: 3.0881. Min Range: -3.0881

Max Act: 3.0043. Min Act: -0.1700

Data Index: 7565749 (Open Web Text)

Max Activating Token Index: 661

Text #2

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.9945. Min Act: -0.1700

Data Index: 493533 (Open Web Text)

Max Activating Token Index: 545

Text #3

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8958. Min Act: -0.1700

Data Index: 4501434 (Open Web Text)

Max Activating Token Index: 171

Text #4

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.9072. Min Act: -0.1700

Data Index: 6570197 (Open Web Text)

Max Activating Token Index: 991

Text #5

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8657. Min Act: -0.1700

Data Index: 692141 (Open Web Text)

Max Activating Token Index: 900

Text #6

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8816. Min Act: -0.1700

Data Index: 2060212 (Open Web Text)

Max Activating Token Index: 260

Text #7

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8735. Min Act: -0.1700

Data Index: 8831616 (Open Web Text)

Max Activating Token Index: 144

Text #8

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8756. Min Act: -0.1700

Data Index: 2577567 (Open Web Text)

Max Activating Token Index: 459

Text #9

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8356. Min Act: -0.1700

Data Index: 7437718 (Open Web Text)

Max Activating Token Index: 471

Text #10

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8556. Min Act: -0.1700

Data Index: 8787100 (Open Web Text)

Max Activating Token Index: 864

Text #11

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8560. Min Act: -0.1700

Data Index: 140544 (Open Web Text)

Max Activating Token Index: 175

Text #12

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.7486. Min Act: -0.1700

Data Index: 5873190 (Open Web Text)

Max Activating Token Index: 885

Text #13

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8238. Min Act: -0.1700

Data Index: 4717252 (Open Web Text)

Max Activating Token Index: 140

Text #14

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8212. Min Act: -0.1700

Data Index: 5427029 (Open Web Text)

Max Activating Token Index: 705

Text #15

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8070. Min Act: -0.1700

Data Index: 434767 (Open Web Text)

Max Activating Token Index: 647

Text #16

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8004. Min Act: -0.1700

Data Index: 4239030 (Open Web Text)

Max Activating Token Index: 324

Text #17

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8097. Min Act: -0.1700

Data Index: 6365649 (Open Web Text)

Max Activating Token Index: 201

Text #18

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8236. Min Act: -0.1700

Data Index: 6334893 (Open Web Text)

Max Activating Token Index: 55

Text #19

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8291. Min Act: -0.1700

Data Index: 1599401 (Open Web Text)

Max Activating Token Index: 413