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

Dataset: Open Web Text

Neuron 2803 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: 0.7303. Min Range: -0.7303

Max Act: 0.7303. Min Act: -0.1700

Data Index: 1834307 (Open Web Text)

Max Activating Token Index: 237

Text #1

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.7115. Min Act: -0.1700

Data Index: 5195378 (Open Web Text)

Max Activating Token Index: 253

Text #2

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.7134. Min Act: -0.1700

Data Index: 7054479 (Open Web Text)

Max Activating Token Index: 253

Text #3

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.7061. Min Act: -0.1700

Data Index: 6401678 (Open Web Text)

Max Activating Token Index: 248

Text #4

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.7033. Min Act: -0.1700

Data Index: 598689 (Open Web Text)

Max Activating Token Index: 832

Text #5

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.7001. Min Act: -0.1700

Data Index: 5341728 (Open Web Text)

Max Activating Token Index: 259

Text #6

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6954. Min Act: -0.1700

Data Index: 7843064 (Open Web Text)

Max Activating Token Index: 259

Text #7

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6970. Min Act: -0.1700

Data Index: 8782386 (Open Web Text)

Max Activating Token Index: 238

Text #8

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6902. Min Act: -0.1700

Data Index: 7403594 (Open Web Text)

Max Activating Token Index: 830

Text #9

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.7000. Min Act: -0.1700

Data Index: 1714618 (Open Web Text)

Max Activating Token Index: 247

Text #10

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6968. Min Act: -0.1700

Data Index: 7734991 (Open Web Text)

Max Activating Token Index: 250

Text #11

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6951. Min Act: -0.1700

Data Index: 4130187 (Open Web Text)

Max Activating Token Index: 250

Text #12

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6884. Min Act: -0.1700

Data Index: 616405 (Open Web Text)

Max Activating Token Index: 246

Text #13

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6939. Min Act: -0.1700

Data Index: 6035351 (Open Web Text)

Max Activating Token Index: 241

Text #14

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6922. Min Act: -0.1700

Data Index: 8167645 (Open Web Text)

Max Activating Token Index: 256

Text #15

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6907. Min Act: -0.1700

Data Index: 6123542 (Open Web Text)

Max Activating Token Index: 245

Text #16

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6923. Min Act: -0.1700

Data Index: 1144045 (Open Web Text)

Max Activating Token Index: 250

Text #17

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.7002. Min Act: -0.1700

Data Index: 8823938 (Open Web Text)

Max Activating Token Index: 230

Text #18

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6914. Min Act: -0.1700

Data Index: 7505936 (Open Web Text)

Max Activating Token Index: 252

Text #19

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6834. Min Act: -0.1700

Data Index: 2541470 (Open Web Text)

Max Activating Token Index: 249