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

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

Neuron 2959 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1359. Min Act: -0.0000

Data Index: 1414615 (Python Code)

Max Activating Token Index: 55

Text #1

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1163. Min Act: -0.0000

Data Index: 701752 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1138. Min Act: -0.0000

Data Index: 832714 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1074. Min Act: -0.0000

Data Index: 28698 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1010. Min Act: -0.0001

Data Index: 251588 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1101. Min Act: -0.0000

Data Index: 1459649 (Python Code)

Max Activating Token Index: 122

Text #6

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1027. Min Act: -0.0000

Data Index: 1424618 (Python Code)

Max Activating Token Index: 108

Text #7

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0978. Min Act: -0.0000

Data Index: 458239 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0931. Min Act: -0.0000

Data Index: 87151 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1022. Min Act: -0.0000

Data Index: 268765 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1025. Min Act: -0.0000

Data Index: 198778 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1065. Min Act: -0.0001

Data Index: 546396 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0973. Min Act: -0.0001

Data Index: 103004 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1012. Min Act: -0.0000

Data Index: 73254 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0982. Min Act: -0.0001

Data Index: 965727 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0974. Min Act: -0.0000

Data Index: 1209905 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0956. Min Act: -0.0000

Data Index: 1525653 (Python Code)

Max Activating Token Index: 398

Text #17

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0968. Min Act: -0.0000

Data Index: 1431135 (Python Code)

Max Activating Token Index: 49

Text #18

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1039. Min Act: -0.0001

Data Index: 946547 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0939. Min Act: -0.0000

Data Index: 719383 (C4 (Web Text))

Max Activating Token Index: 763