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

Dataset: Open Web Text

Neuron 2331 in Layer 1

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: 4.1924. Min Range: -4.1924

Max Act: 4.1924. Min Act: -0.1700

Data Index: 5959714 (Open Web Text)

Max Activating Token Index: 24

Text #1

Max Range: 4.1924. Min Range: -4.1924

Max Act: 4.1661. Min Act: -0.1699

Data Index: 7591291 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.1924. Min Range: -4.1924

Max Act: 4.1661. Min Act: -0.1700

Data Index: 3380595 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.1924. Min Range: -4.1924

Max Act: 4.1312. Min Act: -0.1700

Data Index: 8313715 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.1924. Min Range: -4.1924

Max Act: 4.1312. Min Act: -0.1700

Data Index: 7727758 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.1924. Min Range: -4.1924

Max Act: 4.1312. Min Act: -0.1700

Data Index: 1901783 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.1924. Min Range: -4.1924

Max Act: 4.1312. Min Act: -0.1700

Data Index: 6057448 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.1924. Min Range: -4.1924

Max Act: 4.1312. Min Act: -0.1700

Data Index: 3846191 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 4.1924. Min Range: -4.1924

Max Act: 4.0863. Min Act: -0.1700

Data Index: 990451 (Open Web Text)

Max Activating Token Index: 295

Text #9

Max Range: 4.1924. Min Range: -4.1924

Max Act: 4.0572. Min Act: -0.1700

Data Index: 8762157 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 4.1924. Min Range: -4.1924

Max Act: 4.0434. Min Act: -0.1700

Data Index: 2627580 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 4.1924. Min Range: -4.1924

Max Act: 4.0242. Min Act: -0.1700

Data Index: 6633588 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.1924. Min Range: -4.1924

Max Act: 4.0341. Min Act: -0.1700

Data Index: 206607 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.1924. Min Range: -4.1924

Max Act: 3.9948. Min Act: -0.1700

Data Index: 4109607 (Open Web Text)

Max Activating Token Index: 333

Text #14

Max Range: 4.1924. Min Range: -4.1924

Max Act: 4.0246. Min Act: -0.1700

Data Index: 5338309 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.1924. Min Range: -4.1924

Max Act: 3.9958. Min Act: -0.1700

Data Index: 5176036 (Open Web Text)

Max Activating Token Index: 595

Text #16

Max Range: 4.1924. Min Range: -4.1924

Max Act: 4.0246. Min Act: -0.1700

Data Index: 7320677 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.1924. Min Range: -4.1924

Max Act: 4.0152. Min Act: -0.1700

Data Index: 28815 (Open Web Text)

Max Activating Token Index: 189

Text #18

Max Range: 4.1924. Min Range: -4.1924

Max Act: 4.0069. Min Act: -0.1700

Data Index: 5048027 (Open Web Text)

Max Activating Token Index: 559

Text #19

Max Range: 4.1924. Min Range: -4.1924

Max Act: 4.0121. Min Act: -0.1700

Data Index: 2274482 (Open Web Text)

Max Activating Token Index: 5