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

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

Neuron 1931 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3957. Min Act: -0.0001

Data Index: 775522 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3537. Min Act: -0.0001

Data Index: 340509 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3239. Min Act: -0.0001

Data Index: 234611 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3179. Min Act: -0.0001

Data Index: 248335 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.2973. Min Act: -0.0001

Data Index: 899329 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.2962. Min Act: -0.0001

Data Index: 245474 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.2851. Min Act: -0.0001

Data Index: 570230 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.2664. Min Act: -0.0001

Data Index: 310854 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.2938. Min Act: -0.0001

Data Index: 1240691 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.2823. Min Act: -0.0001

Data Index: 755169 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.2786. Min Act: -0.0001

Data Index: 355707 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.2801. Min Act: -0.0001

Data Index: 452784 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.2704. Min Act: -0.0001

Data Index: 125706 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.2704. Min Act: -0.0001

Data Index: 1137839 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.2739. Min Act: -0.0001

Data Index: 416209 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.2655. Min Act: -0.0001

Data Index: 935754 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.2682. Min Act: -0.0001

Data Index: 242016 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.2514. Min Act: -0.0001

Data Index: 1155700 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.2701. Min Act: -0.0001

Data Index: 911485 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.2557. Min Act: -0.0001

Data Index: 204808 (C4 (Web Text))

Max Activating Token Index: 832