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

Dataset: Open Web Text

Neuron 1899 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: 4.3596. Min Range: -4.3596

Max Act: 4.3596. Min Act: -0.1700

Data Index: 5917570 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.3596. Min Range: -4.3596

Max Act: 4.3396. Min Act: -0.1700

Data Index: 1357937 (Open Web Text)

Max Activating Token Index: 17

Text #2

Max Range: 4.3596. Min Range: -4.3596

Max Act: 4.3271. Min Act: -0.1700

Data Index: 3304675 (Open Web Text)

Max Activating Token Index: 247

Text #3

Max Range: 4.3596. Min Range: -4.3596

Max Act: 4.2510. Min Act: -0.1700

Data Index: 1219556 (Open Web Text)

Max Activating Token Index: 381

Text #4

Max Range: 4.3596. Min Range: -4.3596

Max Act: 4.2537. Min Act: -0.1700

Data Index: 5921991 (Open Web Text)

Max Activating Token Index: 269

Text #5

Max Range: 4.3596. Min Range: -4.3596

Max Act: 4.2319. Min Act: -0.1700

Data Index: 8414863 (Open Web Text)

Max Activating Token Index: 337

Text #6

Max Range: 4.3596. Min Range: -4.3596

Max Act: 4.2271. Min Act: -0.1700

Data Index: 2880891 (Open Web Text)

Max Activating Token Index: 25

Text #7

Max Range: 4.3596. Min Range: -4.3596

Max Act: 4.2308. Min Act: -0.1700

Data Index: 5778278 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.3596. Min Range: -4.3596

Max Act: 4.1871. Min Act: -0.1700

Data Index: 5163176 (Open Web Text)

Max Activating Token Index: 274

Text #9

Max Range: 4.3596. Min Range: -4.3596

Max Act: 4.2013. Min Act: -0.1700

Data Index: 6018432 (Open Web Text)

Max Activating Token Index: 318

Text #10

Max Range: 4.3596. Min Range: -4.3596

Max Act: 4.1995. Min Act: -0.1700

Data Index: 874749 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.3596. Min Range: -4.3596

Max Act: 4.1979. Min Act: -0.1700

Data Index: 4086750 (Open Web Text)

Max Activating Token Index: 171

Text #12

Max Range: 4.3596. Min Range: -4.3596

Max Act: 4.2060. Min Act: -0.1700

Data Index: 3098787 (Open Web Text)

Max Activating Token Index: 673

Text #13

Max Range: 4.3596. Min Range: -4.3596

Max Act: 4.2154. Min Act: -0.1700

Data Index: 5573548 (Open Web Text)

Max Activating Token Index: 315

Text #14

Max Range: 4.3596. Min Range: -4.3596

Max Act: 4.1973. Min Act: -0.1700

Data Index: 5340554 (Open Web Text)

Max Activating Token Index: 15

Text #15

Max Range: 4.3596. Min Range: -4.3596

Max Act: 4.2111. Min Act: -0.1700

Data Index: 2891465 (Open Web Text)

Max Activating Token Index: 247

Text #16

Max Range: 4.3596. Min Range: -4.3596

Max Act: 4.2033. Min Act: -0.1700

Data Index: 3741532 (Open Web Text)

Max Activating Token Index: 311

Text #17

Max Range: 4.3596. Min Range: -4.3596

Max Act: 4.2194. Min Act: -0.1700

Data Index: 2353917 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 4.3596. Min Range: -4.3596

Max Act: 4.1874. Min Act: -0.1700

Data Index: 5324837 (Open Web Text)

Max Activating Token Index: 187

Text #19

Max Range: 4.3596. Min Range: -4.3596

Max Act: 4.1930. Min Act: -0.1700

Data Index: 2241136 (Open Web Text)

Max Activating Token Index: 5