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

Dataset: Open Web Text

Neuron 2500 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: 3.8005. Min Range: -3.8005

Max Act: 3.8005. Min Act: -0.1700

Data Index: 5984191 (Open Web Text)

Max Activating Token Index: 206

Text #1

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.7155. Min Act: -0.1700

Data Index: 4824024 (Open Web Text)

Max Activating Token Index: 507

Text #2

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.6713. Min Act: -0.1700

Data Index: 4664909 (Open Web Text)

Max Activating Token Index: 476

Text #3

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.6686. Min Act: -0.1700

Data Index: 7925032 (Open Web Text)

Max Activating Token Index: 444

Text #4

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.5952. Min Act: -0.1700

Data Index: 269187 (Open Web Text)

Max Activating Token Index: 729

Text #5

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.5523. Min Act: -0.1700

Data Index: 3016536 (Open Web Text)

Max Activating Token Index: 412

Text #6

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.6057. Min Act: -0.1700

Data Index: 6389728 (Open Web Text)

Max Activating Token Index: 440

Text #7

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.5930. Min Act: -0.1700

Data Index: 2248409 (Open Web Text)

Max Activating Token Index: 832

Text #8

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.5847. Min Act: -0.1700

Data Index: 8410294 (Open Web Text)

Max Activating Token Index: 69

Text #9

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.6051. Min Act: -0.1700

Data Index: 405446 (Open Web Text)

Max Activating Token Index: 834

Text #10

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.5484. Min Act: -0.1700

Data Index: 5810167 (Open Web Text)

Max Activating Token Index: 909

Text #11

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.5610. Min Act: -0.1700

Data Index: 6384987 (Open Web Text)

Max Activating Token Index: 444

Text #12

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.4777. Min Act: -0.1700

Data Index: 8777965 (Open Web Text)

Max Activating Token Index: 1022

Text #13

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.5530. Min Act: -0.1700

Data Index: 3637809 (Open Web Text)

Max Activating Token Index: 68

Text #14

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.5707. Min Act: -0.1700

Data Index: 4796617 (Open Web Text)

Max Activating Token Index: 892

Text #15

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.5559. Min Act: -0.1700

Data Index: 441278 (Open Web Text)

Max Activating Token Index: 19

Text #16

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.5521. Min Act: -0.1700

Data Index: 5579177 (Open Web Text)

Max Activating Token Index: 73

Text #17

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.5516. Min Act: -0.1700

Data Index: 2820646 (Open Web Text)

Max Activating Token Index: 1008

Text #18

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.5130. Min Act: -0.1700

Data Index: 2004180 (Open Web Text)

Max Activating Token Index: 350

Text #19

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.4866. Min Act: -0.1700

Data Index: 7107351 (Open Web Text)

Max Activating Token Index: 418