Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1608 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.8284. Min Act: -0.1700

Data Index: 446321 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.8199. Min Act: -0.1700

Data Index: 1171383 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.8027. Min Act: -0.1700

Data Index: 785516 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.8027. Min Act: -0.1700

Data Index: 638311 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.7769. Min Act: -0.1700

Data Index: 1309256 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.7769. Min Act: -0.1700

Data Index: 913393 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.7683. Min Act: -0.1700

Data Index: 599559 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.7683. Min Act: -0.1700

Data Index: 276728 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.7683. Min Act: -0.1700

Data Index: 875793 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.7683. Min Act: -0.1700

Data Index: 1259850 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.7683. Min Act: -0.1700

Data Index: 1141878 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.7596. Min Act: -0.1700

Data Index: 1503450 (Python Code)

Max Activating Token Index: 61

Text #12

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.7596. Min Act: -0.1700

Data Index: 1241017 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.7683. Min Act: -0.1700

Data Index: 1232523 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.7596. Min Act: -0.1700

Data Index: 1002027 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.7596. Min Act: -0.1700

Data Index: 241376 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.7596. Min Act: -0.1700

Data Index: 584056 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.7337. Min Act: -0.1700

Data Index: 829220 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.7510. Min Act: -0.1700

Data Index: 1070706 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.7424. Min Act: -0.1700

Data Index: 941098 (C4 (Web Text))

Max Activating Token Index: 52