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

Dataset: Open Web Text

Neuron 2664 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: 3.2166. Min Range: -3.2166

Max Act: 3.2166. Min Act: -0.1608

Data Index: 19470 (Open Web Text)

Max Activating Token Index: 1

Text #1

Max Range: 3.2166. Min Range: -3.2166

Max Act: 3.2166. Min Act: 0.0284

Data Index: 61061 (Open Web Text)

Max Activating Token Index: 1

Text #2

Max Range: 3.2166. Min Range: -3.2166

Max Act: 3.2166. Min Act: -0.0400

Data Index: 9630 (Open Web Text)

Max Activating Token Index: 1

Text #3

Max Range: 3.2166. Min Range: -3.2166

Max Act: 3.2166. Min Act: -0.0208

Data Index: 8786 (Open Web Text)

Max Activating Token Index: 1

Text #4

Max Range: 3.2166. Min Range: -3.2166

Max Act: 3.2166. Min Act: 0.0353

Data Index: 65530 (Open Web Text)

Max Activating Token Index: 1

Text #5

Max Range: 3.2166. Min Range: -3.2166

Max Act: 3.2166. Min Act: 0.1052

Data Index: 52602 (Open Web Text)

Max Activating Token Index: 1

Text #6

Max Range: 3.2166. Min Range: -3.2166

Max Act: 3.2166. Min Act: -0.0452

Data Index: 64506 (Open Web Text)

Max Activating Token Index: 1

Text #7

Max Range: 3.2166. Min Range: -3.2166

Max Act: 3.2166. Min Act: -0.0506

Data Index: 1357 (Open Web Text)

Max Activating Token Index: 1

Text #8

Max Range: 3.2166. Min Range: -3.2166

Max Act: 3.2166. Min Act: 0.1737

Data Index: 51911 (Open Web Text)

Max Activating Token Index: 1

Text #9

Max Range: 3.2166. Min Range: -3.2166

Max Act: 3.2166. Min Act: -0.1552

Data Index: 51441 (Open Web Text)

Max Activating Token Index: 1

Text #10

Max Range: 3.2166. Min Range: -3.2166

Max Act: 3.2166. Min Act: 0.0085

Data Index: 21132 (Open Web Text)

Max Activating Token Index: 1

Text #11

Max Range: 3.2166. Min Range: -3.2166

Max Act: 3.2166. Min Act: -0.0909

Data Index: 7104 (Open Web Text)

Max Activating Token Index: 1

Text #12

Max Range: 3.2166. Min Range: -3.2166

Max Act: 3.2166. Min Act: -0.0154

Data Index: 43115 (Open Web Text)

Max Activating Token Index: 1

Text #13

Max Range: 3.2166. Min Range: -3.2166

Max Act: 3.2166. Min Act: -0.0999

Data Index: 63993 (Open Web Text)

Max Activating Token Index: 1

Text #14

Max Range: 3.2166. Min Range: -3.2166

Max Act: 3.2166. Min Act: -0.0662

Data Index: 35488 (Open Web Text)

Max Activating Token Index: 1

Text #15

Max Range: 3.2166. Min Range: -3.2166

Max Act: 3.2166. Min Act: -0.0511

Data Index: 31940 (Open Web Text)

Max Activating Token Index: 1

Text #16

Max Range: 3.2166. Min Range: -3.2166

Max Act: 3.2166. Min Act: -0.0205

Data Index: 30223 (Open Web Text)

Max Activating Token Index: 1

Text #17

Max Range: 3.2166. Min Range: -3.2166

Max Act: 3.2166. Min Act: 0.0258

Data Index: 24816 (Open Web Text)

Max Activating Token Index: 1

Text #18

Max Range: 3.2166. Min Range: -3.2166

Max Act: 3.2166. Min Act: -0.1386

Data Index: 10284 (Open Web Text)

Max Activating Token Index: 1

Text #19

Max Range: 3.2166. Min Range: -3.2166

Max Act: 3.2166. Min Act: -0.1315

Data Index: 24428 (Open Web Text)

Max Activating Token Index: 1