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

Dataset: Open Web Text

Neuron 144 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: 1.8678. Min Range: -1.8678

Max Act: 1.8678. Min Act: -0.1700

Data Index: 939066 (Open Web Text)

Max Activating Token Index: 110

Text #1

Max Range: 1.8678. Min Range: -1.8678

Max Act: 1.8472. Min Act: -0.1700

Data Index: 4042254 (Open Web Text)

Max Activating Token Index: 107

Text #2

Max Range: 1.8678. Min Range: -1.8678

Max Act: 1.8512. Min Act: -0.1700

Data Index: 2203252 (Open Web Text)

Max Activating Token Index: 133

Text #3

Max Range: 1.8678. Min Range: -1.8678

Max Act: 1.8501. Min Act: -0.1700

Data Index: 6778099 (Open Web Text)

Max Activating Token Index: 126

Text #4

Max Range: 1.8678. Min Range: -1.8678

Max Act: 1.8274. Min Act: -0.1700

Data Index: 553502 (Open Web Text)

Max Activating Token Index: 18

Text #5

Max Range: 1.8678. Min Range: -1.8678

Max Act: 1.8262. Min Act: -0.1700

Data Index: 3115720 (Open Web Text)

Max Activating Token Index: 70

Text #6

Max Range: 1.8678. Min Range: -1.8678

Max Act: 1.8297. Min Act: -0.1700

Data Index: 1659176 (Open Web Text)

Max Activating Token Index: 89

Text #7

Max Range: 1.8678. Min Range: -1.8678

Max Act: 1.8273. Min Act: -0.1700

Data Index: 1571751 (Open Web Text)

Max Activating Token Index: 100

Text #8

Max Range: 1.8678. Min Range: -1.8678

Max Act: 1.8180. Min Act: -0.1700

Data Index: 6444794 (Open Web Text)

Max Activating Token Index: 774

Text #9

Max Range: 1.8678. Min Range: -1.8678

Max Act: 1.8183. Min Act: -0.1700

Data Index: 3583578 (Open Web Text)

Max Activating Token Index: 997

Text #10

Max Range: 1.8678. Min Range: -1.8678

Max Act: 1.7975. Min Act: -0.1700

Data Index: 4861794 (Open Web Text)

Max Activating Token Index: 127

Text #11

Max Range: 1.8678. Min Range: -1.8678

Max Act: 1.7931. Min Act: -0.1700

Data Index: 6576384 (Open Web Text)

Max Activating Token Index: 190

Text #12

Max Range: 1.8678. Min Range: -1.8678

Max Act: 1.7862. Min Act: -0.1700

Data Index: 1506893 (Open Web Text)

Max Activating Token Index: 163

Text #13

Max Range: 1.8678. Min Range: -1.8678

Max Act: 1.7833. Min Act: -0.1700

Data Index: 7610325 (Open Web Text)

Max Activating Token Index: 876

Text #14

Max Range: 1.8678. Min Range: -1.8678

Max Act: 1.7918. Min Act: -0.1700

Data Index: 2951056 (Open Web Text)

Max Activating Token Index: 16

Text #15

Max Range: 1.8678. Min Range: -1.8678

Max Act: 1.7908. Min Act: -0.1700

Data Index: 1523952 (Open Web Text)

Max Activating Token Index: 34

Text #16

Max Range: 1.8678. Min Range: -1.8678

Max Act: 1.7956. Min Act: -0.1700

Data Index: 5520915 (Open Web Text)

Max Activating Token Index: 11

Text #17

Max Range: 1.8678. Min Range: -1.8678

Max Act: 1.7887. Min Act: -0.1699

Data Index: 3502093 (Open Web Text)

Max Activating Token Index: 428

Text #18

Max Range: 1.8678. Min Range: -1.8678

Max Act: 1.7785. Min Act: -0.1699

Data Index: 1227315 (Open Web Text)

Max Activating Token Index: 1002

Text #19

Max Range: 1.8678. Min Range: -1.8678

Max Act: 1.7806. Min Act: -0.1700

Data Index: 6690912 (Open Web Text)

Max Activating Token Index: 83