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

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

Neuron 5666 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3975. Min Act: -0.0000

Data Index: 659500 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3674. Min Act: -0.0000

Data Index: 1005709 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3484. Min Act: -0.0000

Data Index: 49071 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3491. Min Act: -0.0000

Data Index: 63041 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3050. Min Act: -0.0000

Data Index: 617117 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3121. Min Act: -0.0000

Data Index: 413582 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3131. Min Act: -0.0000

Data Index: 168137 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3093. Min Act: -0.0000

Data Index: 878633 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3319. Min Act: -0.0000

Data Index: 624388 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2969. Min Act: -0.0000

Data Index: 1027869 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3069. Min Act: -0.0000

Data Index: 1175550 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3259. Min Act: -0.0000

Data Index: 299351 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3074. Min Act: -0.0000

Data Index: 1157145 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3072. Min Act: -0.0000

Data Index: 49247 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3062. Min Act: -0.0000

Data Index: 1315094 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2953. Min Act: -0.0000

Data Index: 244442 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2945. Min Act: -0.0000

Data Index: 1129037 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2814. Min Act: -0.0000

Data Index: 1243472 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2856. Min Act: -0.0000

Data Index: 11807 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2836. Min Act: -0.0000

Data Index: 998242 (C4 (Web Text))

Max Activating Token Index: 434