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

Dataset: Open Web Text

Neuron 2989 in Layer 6

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: 5.9948. Min Range: -5.9948

Max Act: 5.9948. Min Act: -0.1700

Data Index: 722404 (Open Web Text)

Max Activating Token Index: 204

Text #1

Max Range: 5.9948. Min Range: -5.9948

Max Act: 5.9348. Min Act: -0.1700

Data Index: 2278124 (Open Web Text)

Max Activating Token Index: 110

Text #2

Max Range: 5.9948. Min Range: -5.9948

Max Act: 5.9115. Min Act: -0.1700

Data Index: 7594849 (Open Web Text)

Max Activating Token Index: 280

Text #3

Max Range: 5.9948. Min Range: -5.9948

Max Act: 5.8824. Min Act: -0.1700

Data Index: 8176038 (Open Web Text)

Max Activating Token Index: 367

Text #4

Max Range: 5.9948. Min Range: -5.9948

Max Act: 5.9245. Min Act: -0.1700

Data Index: 3162276 (Open Web Text)

Max Activating Token Index: 409

Text #5

Max Range: 5.9948. Min Range: -5.9948

Max Act: 5.8689. Min Act: -0.1700

Data Index: 3027631 (Open Web Text)

Max Activating Token Index: 527

Text #6

Max Range: 5.9948. Min Range: -5.9948

Max Act: 5.8453. Min Act: -0.1700

Data Index: 2659369 (Open Web Text)

Max Activating Token Index: 272

Text #7

Max Range: 5.9948. Min Range: -5.9948

Max Act: 5.8074. Min Act: -0.1700

Data Index: 2045418 (Open Web Text)

Max Activating Token Index: 123

Text #8

Max Range: 5.9948. Min Range: -5.9948

Max Act: 5.7883. Min Act: -0.1700

Data Index: 650040 (Open Web Text)

Max Activating Token Index: 518

Text #9

Max Range: 5.9948. Min Range: -5.9948

Max Act: 5.7886. Min Act: -0.1700

Data Index: 5924244 (Open Web Text)

Max Activating Token Index: 438

Text #10

Max Range: 5.9948. Min Range: -5.9948

Max Act: 5.8095. Min Act: -0.1700

Data Index: 5233668 (Open Web Text)

Max Activating Token Index: 584

Text #11

Max Range: 5.9948. Min Range: -5.9948

Max Act: 5.8488. Min Act: -0.1700

Data Index: 824810 (Open Web Text)

Max Activating Token Index: 990

Text #12

Max Range: 5.9948. Min Range: -5.9948

Max Act: 5.6714. Min Act: -0.1700

Data Index: 5571975 (Open Web Text)

Max Activating Token Index: 601

Text #13

Max Range: 5.9948. Min Range: -5.9948

Max Act: 5.7229. Min Act: -0.1700

Data Index: 32692 (Open Web Text)

Max Activating Token Index: 365

Text #14

Max Range: 5.9948. Min Range: -5.9948

Max Act: 5.6782. Min Act: -0.1700

Data Index: 988424 (Open Web Text)

Max Activating Token Index: 115

Text #15

Max Range: 5.9948. Min Range: -5.9948

Max Act: 5.6780. Min Act: -0.1700

Data Index: 3835926 (Open Web Text)

Max Activating Token Index: 882

Text #16

Max Range: 5.9948. Min Range: -5.9948

Max Act: 5.6853. Min Act: -0.1700

Data Index: 4228465 (Open Web Text)

Max Activating Token Index: 428

Text #17

Max Range: 5.9948. Min Range: -5.9948

Max Act: 5.5802. Min Act: -0.1700

Data Index: 7101811 (Open Web Text)

Max Activating Token Index: 238

Text #18

Max Range: 5.9948. Min Range: -5.9948

Max Act: 5.6435. Min Act: -0.1700

Data Index: 7746023 (Open Web Text)

Max Activating Token Index: 309

Text #19

Max Range: 5.9948. Min Range: -5.9948

Max Act: 5.6313. Min Act: -0.1700

Data Index: 7891437 (Open Web Text)

Max Activating Token Index: 766