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

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

Neuron 5080 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4009. Min Range: -0.4009

Max Act: 0.3971. Min Act: -0.0000

Data Index: 404389 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 0.4009. Min Range: -0.4009

Max Act: 0.4009. Min Act: -0.0000

Data Index: 1142669 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 0.4009. Min Range: -0.4009

Max Act: 0.3261. Min Act: -0.0000

Data Index: 948663 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.4009. Min Range: -0.4009

Max Act: 0.3471. Min Act: -0.0000

Data Index: 1129472 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 0.4009. Min Range: -0.4009

Max Act: 0.3070. Min Act: -0.0000

Data Index: 1337646 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 0.4009. Min Range: -0.4009

Max Act: 0.3055. Min Act: -0.0000

Data Index: 1569353 (Python Code)

Max Activating Token Index: 405

Text #6

Max Range: 0.4009. Min Range: -0.4009

Max Act: 0.3262. Min Act: 0.0000

Data Index: 377703 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 0.4009. Min Range: -0.4009

Max Act: 0.3080. Min Act: -0.0000

Data Index: 446898 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 0.4009. Min Range: -0.4009

Max Act: 0.3162. Min Act: -0.0000

Data Index: 1499221 (Python Code)

Max Activating Token Index: 978

Text #9

Max Range: 0.4009. Min Range: -0.4009

Max Act: 0.3064. Min Act: -0.0000

Data Index: 618426 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 0.4009. Min Range: -0.4009

Max Act: 0.3008. Min Act: -0.0000

Data Index: 1154469 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 0.4009. Min Range: -0.4009

Max Act: 0.3077. Min Act: -0.0000

Data Index: 907240 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 0.4009. Min Range: -0.4009

Max Act: 0.2964. Min Act: -0.0000

Data Index: 1451421 (Python Code)

Max Activating Token Index: 425

Text #13

Max Range: 0.4009. Min Range: -0.4009

Max Act: 0.3021. Min Act: -0.0000

Data Index: 206160 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 0.4009. Min Range: -0.4009

Max Act: 0.2931. Min Act: -0.0000

Data Index: 145136 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 0.4009. Min Range: -0.4009

Max Act: 0.2717. Min Act: -0.0000

Data Index: 942968 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.4009. Min Range: -0.4009

Max Act: 0.2735. Min Act: -0.0000

Data Index: 281837 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 0.4009. Min Range: -0.4009

Max Act: 0.2640. Min Act: -0.0000

Data Index: 898470 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 0.4009. Min Range: -0.4009

Max Act: 0.2655. Min Act: -0.0000

Data Index: 1466502 (Python Code)

Max Activating Token Index: 922

Text #19

Max Range: 0.4009. Min Range: -0.4009

Max Act: 0.2652. Min Act: -0.0000

Data Index: 478808 (C4 (Web Text))

Max Activating Token Index: 559