Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 842 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0034. Min Act: -0.0005

Data Index: 238643 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0034. Min Act: -0.0006

Data Index: 775554 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0033. Min Act: -0.0005

Data Index: 388198 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0033. Min Act: -0.0005

Data Index: 855352 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0032. Min Act: -0.0005

Data Index: 660644 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0033. Min Act: -0.0005

Data Index: 1031505 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0032. Min Act: -0.0005

Data Index: 1303475 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0032. Min Act: -0.0005

Data Index: 207472 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0032. Min Act: -0.0005

Data Index: 111121 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0032. Min Act: -0.0006

Data Index: 1013470 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0031. Min Act: -0.0005

Data Index: 1251504 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0031. Min Act: -0.0006

Data Index: 55537 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0031. Min Act: -0.0005

Data Index: 1139685 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0031. Min Act: -0.0005

Data Index: 1320803 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0031. Min Act: -0.0005

Data Index: 865447 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0031. Min Act: -0.0006

Data Index: 633697 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0031. Min Act: -0.0005

Data Index: 67323 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0031. Min Act: -0.0005

Data Index: 93804 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0031. Min Act: -0.0005

Data Index: 1257964 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0031. Min Act: -0.0006

Data Index: 309455 (C4 (Web Text))

Max Activating Token Index: 113