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

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

Neuron 3751 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2975. Min Act: -0.0001

Data Index: 976643 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2962. Min Act: 0.0000

Data Index: 1280960 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2903. Min Act: -0.0001

Data Index: 395764 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2922. Min Act: -0.0001

Data Index: 1050908 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2894. Min Act: -0.0001

Data Index: 82511 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2832. Min Act: -0.0001

Data Index: 518030 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2842. Min Act: -0.0001

Data Index: 1149311 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2810. Min Act: -0.0001

Data Index: 941445 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2806. Min Act: -0.0001

Data Index: 651692 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2749. Min Act: -0.0001

Data Index: 1128981 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2779. Min Act: -0.0001

Data Index: 1005381 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2728. Min Act: -0.0001

Data Index: 685136 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2721. Min Act: -0.0001

Data Index: 739025 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2758. Min Act: -0.0001

Data Index: 664167 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2711. Min Act: -0.0001

Data Index: 1117663 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2684. Min Act: -0.0001

Data Index: 427432 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2640. Min Act: -0.0001

Data Index: 1301066 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2655. Min Act: -0.0001

Data Index: 377626 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2677. Min Act: -0.0001

Data Index: 407474 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2700. Min Act: -0.0001

Data Index: 1170721 (C4 (Web Text))

Max Activating Token Index: 697