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

Dataset: Open Web Text

Neuron 1549 in Layer 2

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: 5.0338. Min Range: -5.0338

Max Act: 5.0338. Min Act: -0.1700

Data Index: 4609149 (Open Web Text)

Max Activating Token Index: 340

Text #1

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.9851. Min Act: -0.1700

Data Index: 2716865 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.9173. Min Act: -0.1700

Data Index: 8260026 (Open Web Text)

Max Activating Token Index: 537

Text #3

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.8167. Min Act: -0.1700

Data Index: 1559977 (Open Web Text)

Max Activating Token Index: 982

Text #4

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.8588. Min Act: -0.1700

Data Index: 2716866 (Open Web Text)

Max Activating Token Index: 37

Text #5

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.8496. Min Act: -0.1700

Data Index: 3476153 (Open Web Text)

Max Activating Token Index: 967

Text #6

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.8322. Min Act: -0.1700

Data Index: 2208648 (Open Web Text)

Max Activating Token Index: 65

Text #7

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.8181. Min Act: -0.1700

Data Index: 1092724 (Open Web Text)

Max Activating Token Index: 342

Text #8

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.8314. Min Act: -0.1700

Data Index: 7535128 (Open Web Text)

Max Activating Token Index: 442

Text #9

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.7560. Min Act: -0.1700

Data Index: 3662523 (Open Web Text)

Max Activating Token Index: 955

Text #10

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.7516. Min Act: -0.1700

Data Index: 3479809 (Open Web Text)

Max Activating Token Index: 822

Text #11

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.8007. Min Act: -0.1700

Data Index: 3033580 (Open Web Text)

Max Activating Token Index: 434

Text #12

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.8099. Min Act: -0.1700

Data Index: 2043183 (Open Web Text)

Max Activating Token Index: 461

Text #13

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.7882. Min Act: -0.1700

Data Index: 2771010 (Open Web Text)

Max Activating Token Index: 108

Text #14

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.7817. Min Act: -0.1700

Data Index: 7772337 (Open Web Text)

Max Activating Token Index: 586

Text #15

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.7331. Min Act: -0.1700

Data Index: 4857153 (Open Web Text)

Max Activating Token Index: 178

Text #16

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.7553. Min Act: -0.1700

Data Index: 6251501 (Open Web Text)

Max Activating Token Index: 1008

Text #17

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.7657. Min Act: -0.1700

Data Index: 320715 (Open Web Text)

Max Activating Token Index: 47

Text #18

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.7127. Min Act: -0.1700

Data Index: 1408094 (Open Web Text)

Max Activating Token Index: 941

Text #19

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.7583. Min Act: -0.1700

Data Index: 1270725 (Open Web Text)

Max Activating Token Index: 44