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

Dataset: Open Web Text

Neuron 2388 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: 4.2052. Min Range: -4.2052

Max Act: 4.2052. Min Act: -0.1700

Data Index: 7307003 (Open Web Text)

Max Activating Token Index: 858

Text #1

Max Range: 4.2052. Min Range: -4.2052

Max Act: 4.0557. Min Act: -0.1700

Data Index: 8288156 (Open Web Text)

Max Activating Token Index: 208

Text #2

Max Range: 4.2052. Min Range: -4.2052

Max Act: 4.0533. Min Act: -0.1700

Data Index: 3730295 (Open Web Text)

Max Activating Token Index: 431

Text #3

Max Range: 4.2052. Min Range: -4.2052

Max Act: 3.9846. Min Act: -0.1700

Data Index: 2257342 (Open Web Text)

Max Activating Token Index: 34

Text #4

Max Range: 4.2052. Min Range: -4.2052

Max Act: 3.9462. Min Act: -0.1700

Data Index: 8638236 (Open Web Text)

Max Activating Token Index: 129

Text #5

Max Range: 4.2052. Min Range: -4.2052

Max Act: 3.9048. Min Act: -0.1700

Data Index: 6924814 (Open Web Text)

Max Activating Token Index: 460

Text #6

Max Range: 4.2052. Min Range: -4.2052

Max Act: 3.9302. Min Act: -0.1700

Data Index: 7571165 (Open Web Text)

Max Activating Token Index: 97

Text #7

Max Range: 4.2052. Min Range: -4.2052

Max Act: 3.9239. Min Act: -0.1700

Data Index: 5624901 (Open Web Text)

Max Activating Token Index: 429

Text #8

Max Range: 4.2052. Min Range: -4.2052

Max Act: 3.8933. Min Act: -0.1700

Data Index: 5425044 (Open Web Text)

Max Activating Token Index: 248

Text #9

Max Range: 4.2052. Min Range: -4.2052

Max Act: 3.8490. Min Act: -0.1700

Data Index: 4449401 (Open Web Text)

Max Activating Token Index: 910

Text #10

Max Range: 4.2052. Min Range: -4.2052

Max Act: 3.8490. Min Act: -0.1700

Data Index: 7268782 (Open Web Text)

Max Activating Token Index: 329

Text #11

Max Range: 4.2052. Min Range: -4.2052

Max Act: 3.8586. Min Act: -0.1700

Data Index: 5706366 (Open Web Text)

Max Activating Token Index: 71

Text #12

Max Range: 4.2052. Min Range: -4.2052

Max Act: 3.8469. Min Act: -0.1700

Data Index: 1030683 (Open Web Text)

Max Activating Token Index: 133

Text #13

Max Range: 4.2052. Min Range: -4.2052

Max Act: 3.8792. Min Act: -0.1700

Data Index: 4565568 (Open Web Text)

Max Activating Token Index: 372

Text #14

Max Range: 4.2052. Min Range: -4.2052

Max Act: 3.8334. Min Act: -0.1699

Data Index: 3722041 (Open Web Text)

Max Activating Token Index: 1001

Text #15

Max Range: 4.2052. Min Range: -4.2052

Max Act: 3.8303. Min Act: -0.1700

Data Index: 1060223 (Open Web Text)

Max Activating Token Index: 177

Text #16

Max Range: 4.2052. Min Range: -4.2052

Max Act: 3.8294. Min Act: -0.1700

Data Index: 6710034 (Open Web Text)

Max Activating Token Index: 209

Text #17

Max Range: 4.2052. Min Range: -4.2052

Max Act: 3.8020. Min Act: -0.1700

Data Index: 8686197 (Open Web Text)

Max Activating Token Index: 696

Text #18

Max Range: 4.2052. Min Range: -4.2052

Max Act: 3.7890. Min Act: -0.1700

Data Index: 3215306 (Open Web Text)

Max Activating Token Index: 203

Text #19

Max Range: 4.2052. Min Range: -4.2052

Max Act: 3.7686. Min Act: -0.1700

Data Index: 1509796 (Open Web Text)

Max Activating Token Index: 101