Model: GELU Model: 1 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 894 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.3113. Min Range: -4.3113

Max Act: 4.3113. Min Act: -0.1700

Data Index: 192262 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 4.3113. Min Range: -4.3113

Max Act: 4.2962. Min Act: -0.1700

Data Index: 1214585 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 4.3113. Min Range: -4.3113

Max Act: 4.2477. Min Act: -0.1700

Data Index: 1335401 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 4.3113. Min Range: -4.3113

Max Act: 4.2503. Min Act: -0.1700

Data Index: 851946 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 4.3113. Min Range: -4.3113

Max Act: 4.2315. Min Act: -0.1700

Data Index: 1551742 (Python Code)

Max Activating Token Index: 700

Text #5

Max Range: 4.3113. Min Range: -4.3113

Max Act: 4.2081. Min Act: -0.1700

Data Index: 320672 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 4.3113. Min Range: -4.3113

Max Act: 4.2137. Min Act: -0.1700

Data Index: 504788 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 4.3113. Min Range: -4.3113

Max Act: 4.1958. Min Act: -0.1700

Data Index: 798274 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 4.3113. Min Range: -4.3113

Max Act: 4.1760. Min Act: -0.1700

Data Index: 1200296 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 4.3113. Min Range: -4.3113

Max Act: 4.2156. Min Act: -0.1700

Data Index: 444737 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 4.3113. Min Range: -4.3113

Max Act: 4.1865. Min Act: -0.1700

Data Index: 351078 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 4.3113. Min Range: -4.3113

Max Act: 4.1918. Min Act: -0.1700

Data Index: 52544 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 4.3113. Min Range: -4.3113

Max Act: 4.1863. Min Act: -0.1700

Data Index: 516033 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 4.3113. Min Range: -4.3113

Max Act: 4.1648. Min Act: -0.1700

Data Index: 18504 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 4.3113. Min Range: -4.3113

Max Act: 4.1533. Min Act: -0.1700

Data Index: 675357 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 4.3113. Min Range: -4.3113

Max Act: 4.1641. Min Act: -0.1700

Data Index: 193074 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 4.3113. Min Range: -4.3113

Max Act: 4.1513. Min Act: -0.1700

Data Index: 525973 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 4.3113. Min Range: -4.3113

Max Act: 4.1924. Min Act: -0.1700

Data Index: 1526289 (Python Code)

Max Activating Token Index: 860

Text #18

Max Range: 4.3113. Min Range: -4.3113

Max Act: 4.1444. Min Act: -0.1700

Data Index: 1392407 (Python Code)

Max Activating Token Index: 23

Text #19

Max Range: 4.3113. Min Range: -4.3113

Max Act: 4.1325. Min Act: -0.1700

Data Index: 1216120 (C4 (Web Text))

Max Activating Token Index: 613