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

Dataset: Open Web Text

Neuron 2385 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: 3.2960. Min Range: -3.2960

Max Act: 3.2960. Min Act: -0.1700

Data Index: 4642257 (Open Web Text)

Max Activating Token Index: 651

Text #1

Max Range: 3.2960. Min Range: -3.2960

Max Act: 3.2228. Min Act: -0.1700

Data Index: 4199810 (Open Web Text)

Max Activating Token Index: 958

Text #2

Max Range: 3.2960. Min Range: -3.2960

Max Act: 3.2223. Min Act: -0.1700

Data Index: 533407 (Open Web Text)

Max Activating Token Index: 742

Text #3

Max Range: 3.2960. Min Range: -3.2960

Max Act: 3.2240. Min Act: -0.1700

Data Index: 6929899 (Open Web Text)

Max Activating Token Index: 340

Text #4

Max Range: 3.2960. Min Range: -3.2960

Max Act: 3.1774. Min Act: -0.1700

Data Index: 3818419 (Open Web Text)

Max Activating Token Index: 863

Text #5

Max Range: 3.2960. Min Range: -3.2960

Max Act: 3.1620. Min Act: -0.1700

Data Index: 957247 (Open Web Text)

Max Activating Token Index: 309

Text #6

Max Range: 3.2960. Min Range: -3.2960

Max Act: 3.1664. Min Act: -0.1700

Data Index: 135679 (Open Web Text)

Max Activating Token Index: 374

Text #7

Max Range: 3.2960. Min Range: -3.2960

Max Act: 3.1768. Min Act: -0.1700

Data Index: 2076532 (Open Web Text)

Max Activating Token Index: 164

Text #8

Max Range: 3.2960. Min Range: -3.2960

Max Act: 3.1526. Min Act: -0.1700

Data Index: 7910672 (Open Web Text)

Max Activating Token Index: 102

Text #9

Max Range: 3.2960. Min Range: -3.2960

Max Act: 3.1405. Min Act: -0.1700

Data Index: 225514 (Open Web Text)

Max Activating Token Index: 100

Text #10

Max Range: 3.2960. Min Range: -3.2960

Max Act: 3.1297. Min Act: -0.1700

Data Index: 790503 (Open Web Text)

Max Activating Token Index: 363

Text #11

Max Range: 3.2960. Min Range: -3.2960

Max Act: 3.1356. Min Act: -0.1700

Data Index: 1859845 (Open Web Text)

Max Activating Token Index: 71

Text #12

Max Range: 3.2960. Min Range: -3.2960

Max Act: 3.1405. Min Act: -0.1700

Data Index: 3781115 (Open Web Text)

Max Activating Token Index: 469

Text #13

Max Range: 3.2960. Min Range: -3.2960

Max Act: 3.1065. Min Act: -0.1700

Data Index: 5879557 (Open Web Text)

Max Activating Token Index: 162

Text #14

Max Range: 3.2960. Min Range: -3.2960

Max Act: 3.1109. Min Act: -0.1700

Data Index: 5241586 (Open Web Text)

Max Activating Token Index: 263

Text #15

Max Range: 3.2960. Min Range: -3.2960

Max Act: 3.1067. Min Act: -0.1700

Data Index: 8447495 (Open Web Text)

Max Activating Token Index: 783

Text #16

Max Range: 3.2960. Min Range: -3.2960

Max Act: 3.1102. Min Act: -0.1700

Data Index: 5253297 (Open Web Text)

Max Activating Token Index: 910

Text #17

Max Range: 3.2960. Min Range: -3.2960

Max Act: 3.1154. Min Act: -0.1700

Data Index: 7202501 (Open Web Text)

Max Activating Token Index: 424

Text #18

Max Range: 3.2960. Min Range: -3.2960

Max Act: 3.0893. Min Act: -0.1700

Data Index: 7225209 (Open Web Text)

Max Activating Token Index: 751

Text #19

Max Range: 3.2960. Min Range: -3.2960

Max Act: 3.0836. Min Act: -0.1700

Data Index: 3535713 (Open Web Text)

Max Activating Token Index: 886