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

Dataset: Open Web Text

Neuron 384 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: 3.9003. Min Range: -3.9003

Max Act: 3.8989. Min Act: -0.1700

Data Index: 5770274 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.8868. Min Act: -0.1700

Data Index: 8822592 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.9003. Min Act: -0.1700

Data Index: 5524238 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.8813. Min Act: -0.1700

Data Index: 2136171 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.8472. Min Act: -0.1700

Data Index: 1493194 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.8184. Min Act: -0.1700

Data Index: 1377564 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.8294. Min Act: -0.1700

Data Index: 8759784 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.8184. Min Act: -0.1700

Data Index: 1356535 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.8252. Min Act: -0.1700

Data Index: 5617726 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.8184. Min Act: -0.1700

Data Index: 1116310 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.8294. Min Act: -0.1700

Data Index: 6236013 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.8184. Min Act: -0.1700

Data Index: 4347086 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.7970. Min Act: -0.1700

Data Index: 2311262 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.7884. Min Act: -0.1700

Data Index: 4845282 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.8099. Min Act: -0.1700

Data Index: 4951403 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.7917. Min Act: -0.1700

Data Index: 1943442 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.8030. Min Act: -0.1700

Data Index: 7570070 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.7888. Min Act: -0.1700

Data Index: 7136418 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.7917. Min Act: -0.1700

Data Index: 4336193 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.8076. Min Act: -0.1700

Data Index: 5513556 (Open Web Text)

Max Activating Token Index: 3