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

Dataset: Open Web Text

Neuron 361 in Layer 5

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: 4.9881. Min Range: -4.9881

Max Act: 4.9881. Min Act: -0.1700

Data Index: 3696307 (Open Web Text)

Max Activating Token Index: 104

Text #1

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.9159. Min Act: -0.1700

Data Index: 7423490 (Open Web Text)

Max Activating Token Index: 667

Text #2

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.7495. Min Act: -0.1700

Data Index: 2228272 (Open Web Text)

Max Activating Token Index: 96

Text #3

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.6613. Min Act: -0.1700

Data Index: 1773293 (Open Web Text)

Max Activating Token Index: 752

Text #4

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.5841. Min Act: -0.1700

Data Index: 640074 (Open Web Text)

Max Activating Token Index: 40

Text #5

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.5453. Min Act: -0.1700

Data Index: 5710232 (Open Web Text)

Max Activating Token Index: 691

Text #6

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.5480. Min Act: -0.1700

Data Index: 5390397 (Open Web Text)

Max Activating Token Index: 211

Text #7

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.5281. Min Act: -0.1700

Data Index: 3178093 (Open Web Text)

Max Activating Token Index: 711

Text #8

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.4605. Min Act: -0.1700

Data Index: 1486227 (Open Web Text)

Max Activating Token Index: 149

Text #9

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.4782. Min Act: -0.1700

Data Index: 6538625 (Open Web Text)

Max Activating Token Index: 290

Text #10

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.4656. Min Act: -0.1700

Data Index: 1123144 (Open Web Text)

Max Activating Token Index: 498

Text #11

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.3916. Min Act: -0.1700

Data Index: 7544587 (Open Web Text)

Max Activating Token Index: 776

Text #12

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.3928. Min Act: -0.1700

Data Index: 4383541 (Open Web Text)

Max Activating Token Index: 64

Text #13

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.4141. Min Act: -0.1700

Data Index: 7772837 (Open Web Text)

Max Activating Token Index: 455

Text #14

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.4198. Min Act: -0.1700

Data Index: 1542565 (Open Web Text)

Max Activating Token Index: 876

Text #15

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.3949. Min Act: -0.1700

Data Index: 8140941 (Open Web Text)

Max Activating Token Index: 206

Text #16

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.3951. Min Act: -0.1700

Data Index: 7421196 (Open Web Text)

Max Activating Token Index: 573

Text #17

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.3284. Min Act: -0.1700

Data Index: 4161004 (Open Web Text)

Max Activating Token Index: 122

Text #18

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.3146. Min Act: -0.1700

Data Index: 3581827 (Open Web Text)

Max Activating Token Index: 499

Text #19

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.3452. Min Act: -0.1700

Data Index: 1829119 (Open Web Text)

Max Activating Token Index: 457