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

Dataset: Open Web Text

Neuron 1839 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: 4.8641. Min Range: -4.8641

Max Act: 4.8641. Min Act: -0.1700

Data Index: 1884420 (Open Web Text)

Max Activating Token Index: 378

Text #1

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.7874. Min Act: -0.1700

Data Index: 5137255 (Open Web Text)

Max Activating Token Index: 506

Text #2

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.7979. Min Act: -0.1700

Data Index: 4645271 (Open Web Text)

Max Activating Token Index: 335

Text #3

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.7325. Min Act: -0.1700

Data Index: 621829 (Open Web Text)

Max Activating Token Index: 376

Text #4

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.7545. Min Act: -0.1700

Data Index: 5953257 (Open Web Text)

Max Activating Token Index: 451

Text #5

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.7183. Min Act: -0.1700

Data Index: 8726575 (Open Web Text)

Max Activating Token Index: 425

Text #6

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.6945. Min Act: -0.1700

Data Index: 6497041 (Open Web Text)

Max Activating Token Index: 412

Text #7

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.6839. Min Act: -0.1700

Data Index: 7493996 (Open Web Text)

Max Activating Token Index: 508

Text #8

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.6880. Min Act: -0.1700

Data Index: 6565972 (Open Web Text)

Max Activating Token Index: 10

Text #9

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.7013. Min Act: -0.1700

Data Index: 5174384 (Open Web Text)

Max Activating Token Index: 987

Text #10

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.6991. Min Act: -0.1700

Data Index: 4696266 (Open Web Text)

Max Activating Token Index: 390

Text #11

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.6876. Min Act: -0.1700

Data Index: 5987354 (Open Web Text)

Max Activating Token Index: 285

Text #12

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.7112. Min Act: -0.1700

Data Index: 2449320 (Open Web Text)

Max Activating Token Index: 128

Text #13

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.6961. Min Act: -0.1700

Data Index: 1959290 (Open Web Text)

Max Activating Token Index: 488

Text #14

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.6781. Min Act: -0.1700

Data Index: 5457671 (Open Web Text)

Max Activating Token Index: 163

Text #15

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.6575. Min Act: -0.1700

Data Index: 5441444 (Open Web Text)

Max Activating Token Index: 98

Text #16

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.6632. Min Act: -0.1700

Data Index: 4813142 (Open Web Text)

Max Activating Token Index: 85

Text #17

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.6887. Min Act: -0.1700

Data Index: 3733152 (Open Web Text)

Max Activating Token Index: 150

Text #18

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.6630. Min Act: -0.1700

Data Index: 3437323 (Open Web Text)

Max Activating Token Index: 403

Text #19

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.6518. Min Act: -0.1700

Data Index: 7144177 (Open Web Text)

Max Activating Token Index: 419