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

Dataset: Open Web Text

Neuron 2515 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: 4.7922. Min Range: -4.7922

Max Act: 4.7922. Min Act: -0.1700

Data Index: 6557676 (Open Web Text)

Max Activating Token Index: 635

Text #1

Max Range: 4.7922. Min Range: -4.7922

Max Act: 4.7244. Min Act: -0.1700

Data Index: 3343365 (Open Web Text)

Max Activating Token Index: 561

Text #2

Max Range: 4.7922. Min Range: -4.7922

Max Act: 4.7089. Min Act: -0.1700

Data Index: 5044593 (Open Web Text)

Max Activating Token Index: 1019

Text #3

Max Range: 4.7922. Min Range: -4.7922

Max Act: 4.7667. Min Act: -0.1700

Data Index: 7560963 (Open Web Text)

Max Activating Token Index: 975

Text #4

Max Range: 4.7922. Min Range: -4.7922

Max Act: 4.7080. Min Act: -0.1700

Data Index: 6936505 (Open Web Text)

Max Activating Token Index: 194

Text #5

Max Range: 4.7922. Min Range: -4.7922

Max Act: 4.7303. Min Act: -0.1700

Data Index: 116511 (Open Web Text)

Max Activating Token Index: 930

Text #6

Max Range: 4.7922. Min Range: -4.7922

Max Act: 4.6661. Min Act: -0.1700

Data Index: 2155584 (Open Web Text)

Max Activating Token Index: 665

Text #7

Max Range: 4.7922. Min Range: -4.7922

Max Act: 4.6832. Min Act: -0.1700

Data Index: 6255197 (Open Web Text)

Max Activating Token Index: 503

Text #8

Max Range: 4.7922. Min Range: -4.7922

Max Act: 4.6593. Min Act: -0.1700

Data Index: 7911489 (Open Web Text)

Max Activating Token Index: 889

Text #9

Max Range: 4.7922. Min Range: -4.7922

Max Act: 4.6526. Min Act: -0.1700

Data Index: 4483187 (Open Web Text)

Max Activating Token Index: 395

Text #10

Max Range: 4.7922. Min Range: -4.7922

Max Act: 4.6531. Min Act: -0.1700

Data Index: 6607062 (Open Web Text)

Max Activating Token Index: 574

Text #11

Max Range: 4.7922. Min Range: -4.7922

Max Act: 4.6270. Min Act: -0.1700

Data Index: 5209189 (Open Web Text)

Max Activating Token Index: 23

Text #12

Max Range: 4.7922. Min Range: -4.7922

Max Act: 4.6114. Min Act: -0.1700

Data Index: 5060215 (Open Web Text)

Max Activating Token Index: 945

Text #13

Max Range: 4.7922. Min Range: -4.7922

Max Act: 4.6044. Min Act: -0.1700

Data Index: 6540936 (Open Web Text)

Max Activating Token Index: 698

Text #14

Max Range: 4.7922. Min Range: -4.7922

Max Act: 4.5865. Min Act: -0.1700

Data Index: 7110990 (Open Web Text)

Max Activating Token Index: 869

Text #15

Max Range: 4.7922. Min Range: -4.7922

Max Act: 4.5713. Min Act: -0.1700

Data Index: 7571780 (Open Web Text)

Max Activating Token Index: 1020

Text #16

Max Range: 4.7922. Min Range: -4.7922

Max Act: 4.6003. Min Act: -0.1700

Data Index: 1713534 (Open Web Text)

Max Activating Token Index: 984

Text #17

Max Range: 4.7922. Min Range: -4.7922

Max Act: 4.5524. Min Act: -0.1700

Data Index: 3799630 (Open Web Text)

Max Activating Token Index: 315

Text #18

Max Range: 4.7922. Min Range: -4.7922

Max Act: 4.5774. Min Act: -0.1700

Data Index: 4782385 (Open Web Text)

Max Activating Token Index: 1005

Text #19

Max Range: 4.7922. Min Range: -4.7922

Max Act: 4.4884. Min Act: -0.1700

Data Index: 5121918 (Open Web Text)

Max Activating Token Index: 900