Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2716 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3125. Min Range: -0.3125

Max Act: 0.3125. Min Act: -0.0001

Data Index: 1423796 (Python Code)

Max Activating Token Index: 541

Text #1

Max Range: 0.3125. Min Range: -0.3125

Max Act: 0.2656. Min Act: -0.0001

Data Index: 1265601 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.3125. Min Range: -0.3125

Max Act: 0.2540. Min Act: -0.0001

Data Index: 471439 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.3125. Min Range: -0.3125

Max Act: 0.2470. Min Act: -0.0001

Data Index: 1502883 (Python Code)

Max Activating Token Index: 811

Text #4

Max Range: 0.3125. Min Range: -0.3125

Max Act: 0.2624. Min Act: -0.0001

Data Index: 663635 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 0.3125. Min Range: -0.3125

Max Act: 0.2162. Min Act: -0.0001

Data Index: 267401 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 0.3125. Min Range: -0.3125

Max Act: 0.2299. Min Act: -0.0001

Data Index: 45290 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 0.3125. Min Range: -0.3125

Max Act: 0.2046. Min Act: -0.0001

Data Index: 368897 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.3125. Min Range: -0.3125

Max Act: 0.2011. Min Act: -0.0001

Data Index: 1318880 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 0.3125. Min Range: -0.3125

Max Act: 0.1980. Min Act: -0.0001

Data Index: 1355137 (C4 (Web Text))

Max Activating Token Index: 474

Text #10

Max Range: 0.3125. Min Range: -0.3125

Max Act: 0.2042. Min Act: -0.0001

Data Index: 898280 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.3125. Min Range: -0.3125

Max Act: 0.1967. Min Act: -0.0001

Data Index: 1006076 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 0.3125. Min Range: -0.3125

Max Act: 0.2012. Min Act: -0.0001

Data Index: 46244 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 0.3125. Min Range: -0.3125

Max Act: 0.2066. Min Act: -0.0001

Data Index: 1003472 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.3125. Min Range: -0.3125

Max Act: 0.1936. Min Act: -0.0001

Data Index: 548401 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 0.3125. Min Range: -0.3125

Max Act: 0.1984. Min Act: -0.0001

Data Index: 1632069 (Python Code)

Max Activating Token Index: 822

Text #16

Max Range: 0.3125. Min Range: -0.3125

Max Act: 0.1980. Min Act: -0.0001

Data Index: 1275668 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 0.3125. Min Range: -0.3125

Max Act: 0.1957. Min Act: -0.0001

Data Index: 619981 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 0.3125. Min Range: -0.3125

Max Act: 0.1936. Min Act: -0.0001

Data Index: 1163974 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 0.3125. Min Range: -0.3125

Max Act: 0.2079. Min Act: -0.0001

Data Index: 1516566 (Python Code)

Max Activating Token Index: 662