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

Dataset: Open Web Text

Neuron 931 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: 3.8947. Min Range: -3.8947

Max Act: 3.8947. Min Act: -0.1700

Data Index: 2323693 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.8569. Min Act: -0.1700

Data Index: 698394 (Open Web Text)

Max Activating Token Index: 43

Text #2

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.8648. Min Act: -0.1700

Data Index: 4329217 (Open Web Text)

Max Activating Token Index: 300

Text #3

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.8574. Min Act: -0.1700

Data Index: 7357856 (Open Web Text)

Max Activating Token Index: 699

Text #4

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.8136. Min Act: -0.1700

Data Index: 4393386 (Open Web Text)

Max Activating Token Index: 14

Text #5

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.7555. Min Act: -0.1700

Data Index: 2323695 (Open Web Text)

Max Activating Token Index: 11

Text #6

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.7675. Min Act: -0.1700

Data Index: 8307157 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.7792. Min Act: -0.1700

Data Index: 8468094 (Open Web Text)

Max Activating Token Index: 196

Text #8

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.7765. Min Act: -0.1700

Data Index: 1880928 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.7219. Min Act: -0.1700

Data Index: 7710840 (Open Web Text)

Max Activating Token Index: 925

Text #10

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.7368. Min Act: -0.1700

Data Index: 2323691 (Open Web Text)

Max Activating Token Index: 106

Text #11

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.6988. Min Act: -0.1700

Data Index: 7469198 (Open Web Text)

Max Activating Token Index: 221

Text #12

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.6974. Min Act: -0.1700

Data Index: 2120977 (Open Web Text)

Max Activating Token Index: 23

Text #13

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.7004. Min Act: -0.1700

Data Index: 1118433 (Open Web Text)

Max Activating Token Index: 123

Text #14

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.6874. Min Act: -0.1700

Data Index: 7120621 (Open Web Text)

Max Activating Token Index: 60

Text #15

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.6753. Min Act: -0.1700

Data Index: 1132617 (Open Web Text)

Max Activating Token Index: 300

Text #16

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.6587. Min Act: -0.1700

Data Index: 2323684 (Open Web Text)

Max Activating Token Index: 259

Text #17

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.6852. Min Act: -0.1700

Data Index: 91798 (Open Web Text)

Max Activating Token Index: 189

Text #18

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.6756. Min Act: -0.1700

Data Index: 6564960 (Open Web Text)

Max Activating Token Index: 572

Text #19

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.6487. Min Act: -0.1700

Data Index: 6288211 (Open Web Text)

Max Activating Token Index: 472