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

Dataset: Open Web Text

Neuron 420 in Layer 2

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: 4.7818. Min Range: -4.7818

Max Act: 4.7818. Min Act: -0.1700

Data Index: 2464295 (Open Web Text)

Max Activating Token Index: 96

Text #1

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.7519. Min Act: -0.1700

Data Index: 2961047 (Open Web Text)

Max Activating Token Index: 80

Text #2

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.7134. Min Act: -0.1700

Data Index: 1189247 (Open Web Text)

Max Activating Token Index: 153

Text #3

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.7250. Min Act: -0.1700

Data Index: 3111793 (Open Web Text)

Max Activating Token Index: 22

Text #4

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.7522. Min Act: -0.1700

Data Index: 1683609 (Open Web Text)

Max Activating Token Index: 86

Text #5

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.7212. Min Act: -0.1700

Data Index: 4420443 (Open Web Text)

Max Activating Token Index: 572

Text #6

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.7335. Min Act: -0.1700

Data Index: 8203830 (Open Web Text)

Max Activating Token Index: 67

Text #7

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.6341. Min Act: -0.1700

Data Index: 8452712 (Open Web Text)

Max Activating Token Index: 145

Text #8

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.6787. Min Act: -0.1700

Data Index: 6343604 (Open Web Text)

Max Activating Token Index: 38

Text #9

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.6823. Min Act: -0.1700

Data Index: 1194099 (Open Web Text)

Max Activating Token Index: 477

Text #10

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.5675. Min Act: -0.1700

Data Index: 7298050 (Open Web Text)

Max Activating Token Index: 286

Text #11

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.5842. Min Act: -0.1700

Data Index: 2649919 (Open Web Text)

Max Activating Token Index: 48

Text #12

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.6144. Min Act: -0.1700

Data Index: 1802262 (Open Web Text)

Max Activating Token Index: 64

Text #13

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.6247. Min Act: -0.1700

Data Index: 1117416 (Open Web Text)

Max Activating Token Index: 180

Text #14

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.5461. Min Act: -0.1700

Data Index: 8314579 (Open Web Text)

Max Activating Token Index: 917

Text #15

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.5711. Min Act: -0.1700

Data Index: 754153 (Open Web Text)

Max Activating Token Index: 637

Text #16

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.5795. Min Act: -0.1700

Data Index: 7412263 (Open Web Text)

Max Activating Token Index: 806

Text #17

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.5666. Min Act: -0.1700

Data Index: 6336386 (Open Web Text)

Max Activating Token Index: 132

Text #18

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.5611. Min Act: -0.1700

Data Index: 3430643 (Open Web Text)

Max Activating Token Index: 172

Text #19

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.6020. Min Act: -0.1700

Data Index: 2064112 (Open Web Text)

Max Activating Token Index: 257