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

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

Neuron 1804 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: 3.7852. Min Range: -3.7852

Max Act: 3.7852. Min Act: -0.1700

Data Index: 48779 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 3.7852. Min Range: -3.7852

Max Act: 3.6450. Min Act: -0.1700

Data Index: 955844 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 3.7852. Min Range: -3.7852

Max Act: 3.6197. Min Act: -0.1700

Data Index: 13433 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 3.7852. Min Range: -3.7852

Max Act: 3.5892. Min Act: -0.1700

Data Index: 406042 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 3.7852. Min Range: -3.7852

Max Act: 3.5753. Min Act: -0.1700

Data Index: 32945 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 3.7852. Min Range: -3.7852

Max Act: 3.5680. Min Act: -0.1700

Data Index: 1076402 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 3.7852. Min Range: -3.7852

Max Act: 3.5375. Min Act: -0.1700

Data Index: 738900 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 3.7852. Min Range: -3.7852

Max Act: 3.5487. Min Act: -0.1700

Data Index: 158559 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 3.7852. Min Range: -3.7852

Max Act: 3.5359. Min Act: -0.1700

Data Index: 34094 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 3.7852. Min Range: -3.7852

Max Act: 3.5313. Min Act: -0.1700

Data Index: 168855 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 3.7852. Min Range: -3.7852

Max Act: 3.5077. Min Act: -0.1700

Data Index: 185200 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 3.7852. Min Range: -3.7852

Max Act: 3.4903. Min Act: -0.1700

Data Index: 945297 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 3.7852. Min Range: -3.7852

Max Act: 3.5206. Min Act: -0.1700

Data Index: 342035 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 3.7852. Min Range: -3.7852

Max Act: 3.4981. Min Act: -0.1700

Data Index: 1005113 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 3.7852. Min Range: -3.7852

Max Act: 3.5040. Min Act: -0.1700

Data Index: 269897 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 3.7852. Min Range: -3.7852

Max Act: 3.4992. Min Act: -0.1700

Data Index: 613240 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 3.7852. Min Range: -3.7852

Max Act: 3.4831. Min Act: -0.1700

Data Index: 657392 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 3.7852. Min Range: -3.7852

Max Act: 3.5045. Min Act: -0.1700

Data Index: 790520 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 3.7852. Min Range: -3.7852

Max Act: 3.4914. Min Act: -0.1700

Data Index: 11351 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 3.7852. Min Range: -3.7852

Max Act: 3.4814. Min Act: -0.1700

Data Index: 11703 (C4 (Web Text))

Max Activating Token Index: 788