Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2061 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.3347. Min Act: -0.0001

Data Index: 642659 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.3309. Min Act: -0.0001

Data Index: 28711 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.3048. Min Act: -0.0001

Data Index: 348477 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2806. Min Act: -0.0001

Data Index: 1293304 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2778. Min Act: -0.0001

Data Index: 1357927 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2997. Min Act: -0.0001

Data Index: 737778 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.3048. Min Act: -0.0001

Data Index: 566066 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.3145. Min Act: -0.0001

Data Index: 992234 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.3031. Min Act: -0.0001

Data Index: 234958 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2873. Min Act: -0.0001

Data Index: 1308064 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2823. Min Act: -0.0001

Data Index: 852789 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2826. Min Act: -0.0001

Data Index: 399983 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2701. Min Act: -0.0001

Data Index: 384797 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2752. Min Act: -0.0001

Data Index: 657437 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2838. Min Act: -0.0001

Data Index: 836948 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2793. Min Act: -0.0001

Data Index: 358043 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2728. Min Act: -0.0001

Data Index: 1122332 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2660. Min Act: -0.0001

Data Index: 1261368 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2758. Min Act: -0.0001

Data Index: 924635 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2637. Min Act: -0.0001

Data Index: 771852 (C4 (Web Text))

Max Activating Token Index: 839