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

Dataset: Open Web Text

Neuron 2953 in Layer 4

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: 3.3624. Min Range: -3.3624

Max Act: 3.3624. Min Act: -0.1700

Data Index: 6334233 (Open Web Text)

Max Activating Token Index: 970

Text #1

Max Range: 3.3624. Min Range: -3.3624

Max Act: 3.1945. Min Act: -0.1700

Data Index: 7716972 (Open Web Text)

Max Activating Token Index: 835

Text #2

Max Range: 3.3624. Min Range: -3.3624

Max Act: 3.1892. Min Act: -0.1700

Data Index: 5098064 (Open Web Text)

Max Activating Token Index: 267

Text #3

Max Range: 3.3624. Min Range: -3.3624

Max Act: 3.1935. Min Act: -0.1700

Data Index: 5724531 (Open Web Text)

Max Activating Token Index: 764

Text #4

Max Range: 3.3624. Min Range: -3.3624

Max Act: 3.1595. Min Act: -0.1700

Data Index: 2633376 (Open Web Text)

Max Activating Token Index: 827

Text #5

Max Range: 3.3624. Min Range: -3.3624

Max Act: 3.1399. Min Act: -0.1700

Data Index: 3121724 (Open Web Text)

Max Activating Token Index: 932

Text #6

Max Range: 3.3624. Min Range: -3.3624

Max Act: 3.1447. Min Act: -0.1700

Data Index: 3112922 (Open Web Text)

Max Activating Token Index: 948

Text #7

Max Range: 3.3624. Min Range: -3.3624

Max Act: 3.1242. Min Act: -0.1700

Data Index: 2662571 (Open Web Text)

Max Activating Token Index: 952

Text #8

Max Range: 3.3624. Min Range: -3.3624

Max Act: 3.1248. Min Act: -0.1700

Data Index: 7796614 (Open Web Text)

Max Activating Token Index: 837

Text #9

Max Range: 3.3624. Min Range: -3.3624

Max Act: 3.1105. Min Act: -0.1700

Data Index: 4033176 (Open Web Text)

Max Activating Token Index: 409

Text #10

Max Range: 3.3624. Min Range: -3.3624

Max Act: 3.1107. Min Act: -0.1700

Data Index: 2336047 (Open Web Text)

Max Activating Token Index: 998

Text #11

Max Range: 3.3624. Min Range: -3.3624

Max Act: 3.1218. Min Act: -0.1700

Data Index: 1008268 (Open Web Text)

Max Activating Token Index: 274

Text #12

Max Range: 3.3624. Min Range: -3.3624

Max Act: 3.1115. Min Act: -0.1700

Data Index: 5890310 (Open Web Text)

Max Activating Token Index: 824

Text #13

Max Range: 3.3624. Min Range: -3.3624

Max Act: 3.1161. Min Act: -0.1700

Data Index: 3145085 (Open Web Text)

Max Activating Token Index: 968

Text #14

Max Range: 3.3624. Min Range: -3.3624

Max Act: 3.1212. Min Act: -0.1700

Data Index: 6300935 (Open Web Text)

Max Activating Token Index: 426

Text #15

Max Range: 3.3624. Min Range: -3.3624

Max Act: 3.1016. Min Act: -0.1700

Data Index: 7264583 (Open Web Text)

Max Activating Token Index: 167

Text #16

Max Range: 3.3624. Min Range: -3.3624

Max Act: 3.1491. Min Act: -0.1700

Data Index: 5807686 (Open Web Text)

Max Activating Token Index: 202

Text #17

Max Range: 3.3624. Min Range: -3.3624

Max Act: 3.1010. Min Act: -0.1700

Data Index: 2374440 (Open Web Text)

Max Activating Token Index: 726

Text #18

Max Range: 3.3624. Min Range: -3.3624

Max Act: 3.0735. Min Act: -0.1700

Data Index: 480207 (Open Web Text)

Max Activating Token Index: 789

Text #19

Max Range: 3.3624. Min Range: -3.3624

Max Act: 3.0595. Min Act: -0.1700

Data Index: 5379655 (Open Web Text)

Max Activating Token Index: 335