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

Dataset: Open Web Text

Neuron 563 in Layer 0

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: 3.1086. Min Range: -3.1086

Max Act: 3.1086. Min Act: -0.1700

Data Index: 1834116 (Open Web Text)

Max Activating Token Index: 148

Text #1

Max Range: 3.1086. Min Range: -3.1086

Max Act: 3.0570. Min Act: -0.1700

Data Index: 1853897 (Open Web Text)

Max Activating Token Index: 582

Text #2

Max Range: 3.1086. Min Range: -3.1086

Max Act: 3.0256. Min Act: -0.1700

Data Index: 1619096 (Open Web Text)

Max Activating Token Index: 37

Text #3

Max Range: 3.1086. Min Range: -3.1086

Max Act: 3.0358. Min Act: -0.1700

Data Index: 5974379 (Open Web Text)

Max Activating Token Index: 703

Text #4

Max Range: 3.1086. Min Range: -3.1086

Max Act: 3.0408. Min Act: -0.1700

Data Index: 2535099 (Open Web Text)

Max Activating Token Index: 675

Text #5

Max Range: 3.1086. Min Range: -3.1086

Max Act: 3.0279. Min Act: -0.1700

Data Index: 668855 (Open Web Text)

Max Activating Token Index: 132

Text #6

Max Range: 3.1086. Min Range: -3.1086

Max Act: 2.9981. Min Act: -0.1700

Data Index: 3587083 (Open Web Text)

Max Activating Token Index: 1009

Text #7

Max Range: 3.1086. Min Range: -3.1086

Max Act: 3.0015. Min Act: -0.1700

Data Index: 7125113 (Open Web Text)

Max Activating Token Index: 730

Text #8

Max Range: 3.1086. Min Range: -3.1086

Max Act: 3.0062. Min Act: -0.1700

Data Index: 4296743 (Open Web Text)

Max Activating Token Index: 104

Text #9

Max Range: 3.1086. Min Range: -3.1086

Max Act: 2.9916. Min Act: -0.1700

Data Index: 2667316 (Open Web Text)

Max Activating Token Index: 562

Text #10

Max Range: 3.1086. Min Range: -3.1086

Max Act: 2.9943. Min Act: -0.1700

Data Index: 3074027 (Open Web Text)

Max Activating Token Index: 169

Text #11

Max Range: 3.1086. Min Range: -3.1086

Max Act: 2.9762. Min Act: -0.1700

Data Index: 6723821 (Open Web Text)

Max Activating Token Index: 682

Text #12

Max Range: 3.1086. Min Range: -3.1086

Max Act: 2.9936. Min Act: -0.1700

Data Index: 1297631 (Open Web Text)

Max Activating Token Index: 377

Text #13

Max Range: 3.1086. Min Range: -3.1086

Max Act: 2.9915. Min Act: -0.1700

Data Index: 433667 (Open Web Text)

Max Activating Token Index: 149

Text #14

Max Range: 3.1086. Min Range: -3.1086

Max Act: 2.9853. Min Act: -0.1700

Data Index: 8802851 (Open Web Text)

Max Activating Token Index: 133

Text #15

Max Range: 3.1086. Min Range: -3.1086

Max Act: 2.9952. Min Act: -0.1700

Data Index: 7120850 (Open Web Text)

Max Activating Token Index: 716

Text #16

Max Range: 3.1086. Min Range: -3.1086

Max Act: 2.9693. Min Act: -0.1700

Data Index: 1926149 (Open Web Text)

Max Activating Token Index: 237

Text #17

Max Range: 3.1086. Min Range: -3.1086

Max Act: 2.9658. Min Act: -0.1700

Data Index: 3358115 (Open Web Text)

Max Activating Token Index: 729

Text #18

Max Range: 3.1086. Min Range: -3.1086

Max Act: 2.9768. Min Act: -0.1700

Data Index: 4631793 (Open Web Text)

Max Activating Token Index: 25

Text #19

Max Range: 3.1086. Min Range: -3.1086

Max Act: 2.9581. Min Act: -0.1700

Data Index: 6573779 (Open Web Text)

Max Activating Token Index: 112