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

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

Neuron 1589 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: 3.3121. Min Range: -3.3121

Max Act: 3.3121. Min Act: -0.1699

Data Index: 891109 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.2981. Min Act: -0.1700

Data Index: 632437 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.2851. Min Act: -0.1700

Data Index: 371636 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.2858. Min Act: -0.1700

Data Index: 1357276 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.2706. Min Act: -0.1700

Data Index: 508824 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.2366. Min Act: -0.1699

Data Index: 11408 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.2280. Min Act: -0.1683

Data Index: 1226848 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.2181. Min Act: -0.1700

Data Index: 422894 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.2036. Min Act: -0.1699

Data Index: 1311180 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.2175. Min Act: -0.1700

Data Index: 1338806 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.1986. Min Act: -0.1700

Data Index: 1621697 (Python Code)

Max Activating Token Index: 1000

Text #11

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.1842. Min Act: -0.1700

Data Index: 1606186 (Python Code)

Max Activating Token Index: 881

Text #12

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.2144. Min Act: -0.1700

Data Index: 922125 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.2085. Min Act: -0.1700

Data Index: 1314859 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.1944. Min Act: -0.1700

Data Index: 863208 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.1791. Min Act: -0.1699

Data Index: 941972 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.1895. Min Act: -0.1700

Data Index: 1347285 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.1852. Min Act: -0.1700

Data Index: 499963 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.1866. Min Act: -0.1700

Data Index: 1283861 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.1815. Min Act: -0.1700

Data Index: 583701 (C4 (Web Text))

Max Activating Token Index: 77