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

Dataset: Open Web Text

Neuron 2796 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: 3.5445. Min Range: -3.5445

Max Act: 3.5445. Min Act: -0.1700

Data Index: 627940 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.5445. Min Range: -3.5445

Max Act: 3.1276. Min Act: -0.1700

Data Index: 1873662 (Open Web Text)

Max Activating Token Index: 396

Text #2

Max Range: 3.5445. Min Range: -3.5445

Max Act: 3.0775. Min Act: -0.1700

Data Index: 7556700 (Open Web Text)

Max Activating Token Index: 589

Text #3

Max Range: 3.5445. Min Range: -3.5445

Max Act: 3.0180. Min Act: -0.1700

Data Index: 8724190 (Open Web Text)

Max Activating Token Index: 95

Text #4

Max Range: 3.5445. Min Range: -3.5445

Max Act: 3.0228. Min Act: -0.1700

Data Index: 8750393 (Open Web Text)

Max Activating Token Index: 197

Text #5

Max Range: 3.5445. Min Range: -3.5445

Max Act: 3.0190. Min Act: -0.1700

Data Index: 7330110 (Open Web Text)

Max Activating Token Index: 871

Text #6

Max Range: 3.5445. Min Range: -3.5445

Max Act: 3.0037. Min Act: -0.1700

Data Index: 6269568 (Open Web Text)

Max Activating Token Index: 311

Text #7

Max Range: 3.5445. Min Range: -3.5445

Max Act: 3.0271. Min Act: -0.1700

Data Index: 4137923 (Open Web Text)

Max Activating Token Index: 79

Text #8

Max Range: 3.5445. Min Range: -3.5445

Max Act: 2.9642. Min Act: -0.1700

Data Index: 191540 (Open Web Text)

Max Activating Token Index: 438

Text #9

Max Range: 3.5445. Min Range: -3.5445

Max Act: 2.9645. Min Act: -0.1700

Data Index: 8702297 (Open Web Text)

Max Activating Token Index: 291

Text #10

Max Range: 3.5445. Min Range: -3.5445

Max Act: 2.9284. Min Act: -0.1700

Data Index: 2444214 (Open Web Text)

Max Activating Token Index: 623

Text #11

Max Range: 3.5445. Min Range: -3.5445

Max Act: 2.9443. Min Act: -0.1700

Data Index: 8633728 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 3.5445. Min Range: -3.5445

Max Act: 2.9314. Min Act: -0.1700

Data Index: 8815112 (Open Web Text)

Max Activating Token Index: 131

Text #13

Max Range: 3.5445. Min Range: -3.5445

Max Act: 2.9155. Min Act: -0.1700

Data Index: 922229 (Open Web Text)

Max Activating Token Index: 579

Text #14

Max Range: 3.5445. Min Range: -3.5445

Max Act: 2.9081. Min Act: -0.1700

Data Index: 217068 (Open Web Text)

Max Activating Token Index: 72

Text #15

Max Range: 3.5445. Min Range: -3.5445

Max Act: 2.8824. Min Act: -0.1700

Data Index: 8344035 (Open Web Text)

Max Activating Token Index: 589

Text #16

Max Range: 3.5445. Min Range: -3.5445

Max Act: 2.8890. Min Act: -0.1700

Data Index: 1695344 (Open Web Text)

Max Activating Token Index: 380

Text #17

Max Range: 3.5445. Min Range: -3.5445

Max Act: 2.9076. Min Act: -0.1700

Data Index: 3533391 (Open Web Text)

Max Activating Token Index: 838

Text #18

Max Range: 3.5445. Min Range: -3.5445

Max Act: 2.9135. Min Act: -0.1700

Data Index: 7831892 (Open Web Text)

Max Activating Token Index: 445

Text #19

Max Range: 3.5445. Min Range: -3.5445

Max Act: 2.8616. Min Act: -0.1700

Data Index: 6698019 (Open Web Text)

Max Activating Token Index: 438