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

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

Neuron 1613 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: 3.4512. Min Range: -3.4512

Max Act: 3.4512. Min Act: -0.1700

Data Index: 277646 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 3.4512. Min Range: -3.4512

Max Act: 3.3537. Min Act: -0.1700

Data Index: 570914 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 3.4512. Min Range: -3.4512

Max Act: 3.3527. Min Act: -0.1700

Data Index: 1588347 (Python Code)

Max Activating Token Index: 715

Text #3

Max Range: 3.4512. Min Range: -3.4512

Max Act: 3.2884. Min Act: -0.1700

Data Index: 1223328 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 3.4512. Min Range: -3.4512

Max Act: 3.2803. Min Act: -0.1700

Data Index: 1375850 (Python Code)

Max Activating Token Index: 730

Text #5

Max Range: 3.4512. Min Range: -3.4512

Max Act: 3.2277. Min Act: -0.1700

Data Index: 1420995 (Python Code)

Max Activating Token Index: 784

Text #6

Max Range: 3.4512. Min Range: -3.4512

Max Act: 3.2088. Min Act: -0.1700

Data Index: 419362 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 3.4512. Min Range: -3.4512

Max Act: 3.2085. Min Act: -0.1700

Data Index: 131580 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 3.4512. Min Range: -3.4512

Max Act: 3.2127. Min Act: -0.1700

Data Index: 1379717 (Python Code)

Max Activating Token Index: 925

Text #9

Max Range: 3.4512. Min Range: -3.4512

Max Act: 3.2136. Min Act: -0.1700

Data Index: 980251 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 3.4512. Min Range: -3.4512

Max Act: 3.2030. Min Act: -0.1700

Data Index: 1415696 (Python Code)

Max Activating Token Index: 996

Text #11

Max Range: 3.4512. Min Range: -3.4512

Max Act: 3.1873. Min Act: -0.1700

Data Index: 1414499 (Python Code)

Max Activating Token Index: 641

Text #12

Max Range: 3.4512. Min Range: -3.4512

Max Act: 3.1951. Min Act: -0.1700

Data Index: 1512909 (Python Code)

Max Activating Token Index: 890

Text #13

Max Range: 3.4512. Min Range: -3.4512

Max Act: 3.1934. Min Act: -0.1700

Data Index: 445350 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 3.4512. Min Range: -3.4512

Max Act: 3.1740. Min Act: -0.1700

Data Index: 150654 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 3.4512. Min Range: -3.4512

Max Act: 3.1785. Min Act: -0.1700

Data Index: 1360243 (Python Code)

Max Activating Token Index: 393

Text #16

Max Range: 3.4512. Min Range: -3.4512

Max Act: 3.1644. Min Act: -0.1700

Data Index: 1587954 (Python Code)

Max Activating Token Index: 553

Text #17

Max Range: 3.4512. Min Range: -3.4512

Max Act: 3.1783. Min Act: -0.1700

Data Index: 1456245 (Python Code)

Max Activating Token Index: 15

Text #18

Max Range: 3.4512. Min Range: -3.4512

Max Act: 3.1719. Min Act: -0.1700

Data Index: 322275 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 3.4512. Min Range: -3.4512

Max Act: 3.1785. Min Act: -0.1700

Data Index: 299851 (C4 (Web Text))

Max Activating Token Index: 631