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

Dataset: Open Web Text

Neuron 114 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: 3.4003. Min Range: -3.4003

Max Act: 3.4003. Min Act: -0.1700

Data Index: 5005925 (Open Web Text)

Max Activating Token Index: 577

Text #1

Max Range: 3.4003. Min Range: -3.4003

Max Act: 3.3441. Min Act: -0.1700

Data Index: 2611906 (Open Web Text)

Max Activating Token Index: 284

Text #2

Max Range: 3.4003. Min Range: -3.4003

Max Act: 3.3609. Min Act: -0.1700

Data Index: 534922 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.4003. Min Range: -3.4003

Max Act: 3.2984. Min Act: -0.1700

Data Index: 1259745 (Open Web Text)

Max Activating Token Index: 721

Text #4

Max Range: 3.4003. Min Range: -3.4003

Max Act: 3.3197. Min Act: -0.1700

Data Index: 4453569 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 3.4003. Min Range: -3.4003

Max Act: 3.3108. Min Act: -0.1700

Data Index: 4026939 (Open Web Text)

Max Activating Token Index: 545

Text #6

Max Range: 3.4003. Min Range: -3.4003

Max Act: 3.3113. Min Act: -0.1700

Data Index: 2611110 (Open Web Text)

Max Activating Token Index: 457

Text #7

Max Range: 3.4003. Min Range: -3.4003

Max Act: 3.2993. Min Act: -0.1700

Data Index: 4791992 (Open Web Text)

Max Activating Token Index: 195

Text #8

Max Range: 3.4003. Min Range: -3.4003

Max Act: 3.2744. Min Act: -0.1700

Data Index: 3997210 (Open Web Text)

Max Activating Token Index: 395

Text #9

Max Range: 3.4003. Min Range: -3.4003

Max Act: 3.3073. Min Act: -0.1700

Data Index: 8186139 (Open Web Text)

Max Activating Token Index: 148

Text #10

Max Range: 3.4003. Min Range: -3.4003

Max Act: 3.2616. Min Act: -0.1700

Data Index: 8427737 (Open Web Text)

Max Activating Token Index: 952

Text #11

Max Range: 3.4003. Min Range: -3.4003

Max Act: 3.2870. Min Act: -0.1700

Data Index: 3387224 (Open Web Text)

Max Activating Token Index: 284

Text #12

Max Range: 3.4003. Min Range: -3.4003

Max Act: 3.2670. Min Act: -0.1700

Data Index: 190872 (Open Web Text)

Max Activating Token Index: 523

Text #13

Max Range: 3.4003. Min Range: -3.4003

Max Act: 3.2687. Min Act: -0.1700

Data Index: 6794888 (Open Web Text)

Max Activating Token Index: 563

Text #14

Max Range: 3.4003. Min Range: -3.4003

Max Act: 3.2446. Min Act: -0.1700

Data Index: 1605311 (Open Web Text)

Max Activating Token Index: 616

Text #15

Max Range: 3.4003. Min Range: -3.4003

Max Act: 3.2462. Min Act: -0.1700

Data Index: 6326274 (Open Web Text)

Max Activating Token Index: 324

Text #16

Max Range: 3.4003. Min Range: -3.4003

Max Act: 3.2204. Min Act: -0.1700

Data Index: 3870229 (Open Web Text)

Max Activating Token Index: 221

Text #17

Max Range: 3.4003. Min Range: -3.4003

Max Act: 3.2548. Min Act: -0.1700

Data Index: 251972 (Open Web Text)

Max Activating Token Index: 820

Text #18

Max Range: 3.4003. Min Range: -3.4003

Max Act: 3.2118. Min Act: -0.1700

Data Index: 8115973 (Open Web Text)

Max Activating Token Index: 870

Text #19

Max Range: 3.4003. Min Range: -3.4003

Max Act: 3.2031. Min Act: -0.1700

Data Index: 6532499 (Open Web Text)

Max Activating Token Index: 356