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

Dataset: Open Web Text

Neuron 2860 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: 2.0864. Min Range: -2.0864

Max Act: 2.0864. Min Act: -0.1700

Data Index: 6448878 (Open Web Text)

Max Activating Token Index: 118

Text #1

Max Range: 2.0864. Min Range: -2.0864

Max Act: 2.0839. Min Act: -0.1700

Data Index: 1792912 (Open Web Text)

Max Activating Token Index: 808

Text #2

Max Range: 2.0864. Min Range: -2.0864

Max Act: 2.0777. Min Act: -0.1700

Data Index: 8238941 (Open Web Text)

Max Activating Token Index: 477

Text #3

Max Range: 2.0864. Min Range: -2.0864

Max Act: 2.0502. Min Act: -0.1700

Data Index: 6659642 (Open Web Text)

Max Activating Token Index: 848

Text #4

Max Range: 2.0864. Min Range: -2.0864

Max Act: 2.0315. Min Act: -0.1700

Data Index: 3474400 (Open Web Text)

Max Activating Token Index: 907

Text #5

Max Range: 2.0864. Min Range: -2.0864

Max Act: 2.0270. Min Act: -0.1700

Data Index: 1768064 (Open Web Text)

Max Activating Token Index: 438

Text #6

Max Range: 2.0864. Min Range: -2.0864

Max Act: 2.0423. Min Act: -0.1700

Data Index: 795164 (Open Web Text)

Max Activating Token Index: 710

Text #7

Max Range: 2.0864. Min Range: -2.0864

Max Act: 2.0416. Min Act: -0.1700

Data Index: 6680253 (Open Web Text)

Max Activating Token Index: 98

Text #8

Max Range: 2.0864. Min Range: -2.0864

Max Act: 2.0224. Min Act: -0.1700

Data Index: 684234 (Open Web Text)

Max Activating Token Index: 98

Text #9

Max Range: 2.0864. Min Range: -2.0864

Max Act: 2.0274. Min Act: -0.1700

Data Index: 7297791 (Open Web Text)

Max Activating Token Index: 22

Text #10

Max Range: 2.0864. Min Range: -2.0864

Max Act: 2.0400. Min Act: -0.1700

Data Index: 1303604 (Open Web Text)

Max Activating Token Index: 221

Text #11

Max Range: 2.0864. Min Range: -2.0864

Max Act: 2.0494. Min Act: -0.1700

Data Index: 4949177 (Open Web Text)

Max Activating Token Index: 103

Text #12

Max Range: 2.0864. Min Range: -2.0864

Max Act: 2.0027. Min Act: -0.1700

Data Index: 3427231 (Open Web Text)

Max Activating Token Index: 395

Text #13

Max Range: 2.0864. Min Range: -2.0864

Max Act: 2.0142. Min Act: -0.1700

Data Index: 1106564 (Open Web Text)

Max Activating Token Index: 133

Text #14

Max Range: 2.0864. Min Range: -2.0864

Max Act: 2.0032. Min Act: -0.1700

Data Index: 6813070 (Open Web Text)

Max Activating Token Index: 314

Text #15

Max Range: 2.0864. Min Range: -2.0864

Max Act: 2.0203. Min Act: -0.1700

Data Index: 364256 (Open Web Text)

Max Activating Token Index: 937

Text #16

Max Range: 2.0864. Min Range: -2.0864

Max Act: 2.0145. Min Act: -0.1700

Data Index: 1045736 (Open Web Text)

Max Activating Token Index: 576

Text #17

Max Range: 2.0864. Min Range: -2.0864

Max Act: 2.0049. Min Act: -0.1700

Data Index: 2191847 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 2.0864. Min Range: -2.0864

Max Act: 2.0064. Min Act: -0.1700

Data Index: 6385631 (Open Web Text)

Max Activating Token Index: 93

Text #19

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.9958. Min Act: -0.1700

Data Index: 5055625 (Open Web Text)

Max Activating Token Index: 172