Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3047 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0061. Min Act: -0.0000

Data Index: 295977 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0059. Min Act: -0.0000

Data Index: 1541349 (Python Code)

Max Activating Token Index: 107

Text #2

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0057. Min Act: -0.0001

Data Index: 1190766 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0056. Min Act: -0.0000

Data Index: 587699 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0056. Min Act: -0.0001

Data Index: 181112 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0057. Min Act: -0.0001

Data Index: 720981 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0057. Min Act: -0.0001

Data Index: 707279 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0057. Min Act: -0.0001

Data Index: 1465291 (Python Code)

Max Activating Token Index: 243

Text #8

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0055. Min Act: -0.0000

Data Index: 1481476 (Python Code)

Max Activating Token Index: 135

Text #9

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0057. Min Act: -0.0000

Data Index: 386103 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0056. Min Act: -0.0000

Data Index: 779927 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0053. Min Act: -0.0001

Data Index: 238406 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0054. Min Act: -0.0001

Data Index: 580533 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0053. Min Act: -0.0000

Data Index: 429115 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0053. Min Act: -0.0000

Data Index: 1385034 (Python Code)

Max Activating Token Index: 191

Text #15

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0054. Min Act: -0.0001

Data Index: 714045 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0054. Min Act: -0.0000

Data Index: 728912 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0053. Min Act: -0.0000

Data Index: 1399059 (Python Code)

Max Activating Token Index: 279

Text #18

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0053. Min Act: -0.0001

Data Index: 410761 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0052. Min Act: -0.0000

Data Index: 231435 (C4 (Web Text))

Max Activating Token Index: 102