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

Dataset: Open Web Text

Neuron 1791 in Layer 1

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: 1.9257. Min Range: -1.9257

Max Act: 1.9257. Min Act: -0.1700

Data Index: 7868744 (Open Web Text)

Max Activating Token Index: 233

Text #1

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.8705. Min Act: -0.1700

Data Index: 1942465 (Open Web Text)

Max Activating Token Index: 137

Text #2

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.8542. Min Act: -0.1700

Data Index: 1319004 (Open Web Text)

Max Activating Token Index: 54

Text #3

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.8243. Min Act: -0.1697

Data Index: 2700311 (Open Web Text)

Max Activating Token Index: 163

Text #4

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.8111. Min Act: -0.1700

Data Index: 5120723 (Open Web Text)

Max Activating Token Index: 377

Text #5

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.7975. Min Act: -0.1700

Data Index: 5857488 (Open Web Text)

Max Activating Token Index: 430

Text #6

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.7937. Min Act: -0.1700

Data Index: 4001880 (Open Web Text)

Max Activating Token Index: 168

Text #7

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.7910. Min Act: -0.1700

Data Index: 2137913 (Open Web Text)

Max Activating Token Index: 806

Text #8

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.7961. Min Act: -0.1700

Data Index: 1757089 (Open Web Text)

Max Activating Token Index: 132

Text #9

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.7880. Min Act: -0.1700

Data Index: 6596561 (Open Web Text)

Max Activating Token Index: 194

Text #10

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.7869. Min Act: -0.1700

Data Index: 1942464 (Open Web Text)

Max Activating Token Index: 64

Text #11

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.7678. Min Act: -0.1700

Data Index: 6738160 (Open Web Text)

Max Activating Token Index: 416

Text #12

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.7689. Min Act: -0.1691

Data Index: 2706081 (Open Web Text)

Max Activating Token Index: 52

Text #13

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.7567. Min Act: -0.1700

Data Index: 2144405 (Open Web Text)

Max Activating Token Index: 108

Text #14

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.7638. Min Act: -0.1700

Data Index: 7768800 (Open Web Text)

Max Activating Token Index: 61

Text #15

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.7658. Min Act: -0.1700

Data Index: 7876960 (Open Web Text)

Max Activating Token Index: 235

Text #16

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.7629. Min Act: -0.1697

Data Index: 2137914 (Open Web Text)

Max Activating Token Index: 117

Text #17

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.7582. Min Act: -0.1696

Data Index: 240213 (Open Web Text)

Max Activating Token Index: 166

Text #18

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.7558. Min Act: -0.1700

Data Index: 8179920 (Open Web Text)

Max Activating Token Index: 820

Text #19

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.7424. Min Act: -0.1700

Data Index: 8663427 (Open Web Text)

Max Activating Token Index: 61