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

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

Neuron 1518 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0136. Min Act: -0.0006

Data Index: 990550 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0128. Min Act: -0.0006

Data Index: 458340 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0132. Min Act: -0.0006

Data Index: 329755 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0091. Min Act: -0.0006

Data Index: 543038 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0091. Min Act: -0.0006

Data Index: 1359608 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0079. Min Act: -0.0005

Data Index: 45430 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0066. Min Act: -0.0006

Data Index: 864175 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0075. Min Act: -0.0006

Data Index: 493417 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0074. Min Act: -0.0005

Data Index: 611675 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0070. Min Act: -0.0006

Data Index: 138215 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0067. Min Act: -0.0006

Data Index: 1599875 (Python Code)

Max Activating Token Index: 168

Text #11

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0066. Min Act: -0.0006

Data Index: 1478923 (Python Code)

Max Activating Token Index: 220

Text #12

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0064. Min Act: -0.0006

Data Index: 1419142 (Python Code)

Max Activating Token Index: 74

Text #13

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0062. Min Act: -0.0006

Data Index: 351776 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0062. Min Act: -0.0006

Data Index: 1417359 (Python Code)

Max Activating Token Index: 140

Text #15

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0061. Min Act: -0.0006

Data Index: 1519187 (Python Code)

Max Activating Token Index: 101

Text #16

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0060. Min Act: -0.0006

Data Index: 1432066 (Python Code)

Max Activating Token Index: 75

Text #17

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0060. Min Act: -0.0006

Data Index: 1436073 (Python Code)

Max Activating Token Index: 593

Text #18

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0059. Min Act: -0.0006

Data Index: 1656288 (Python Code)

Max Activating Token Index: 897

Text #19

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0055. Min Act: -0.0006

Data Index: 1620755 (Python Code)

Max Activating Token Index: 444