Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4622 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.3440. Min Act: -0.0001

Data Index: 1296770 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.3026. Min Act: -0.0001

Data Index: 615778 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2991. Min Act: -0.0001

Data Index: 778349 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.3077. Min Act: -0.0001

Data Index: 296774 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2946. Min Act: -0.0001

Data Index: 1283868 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2774. Min Act: -0.0001

Data Index: 397749 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.3112. Min Act: -0.0001

Data Index: 688736 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2974. Min Act: -0.0001

Data Index: 801249 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.3031. Min Act: -0.0001

Data Index: 260626 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2879. Min Act: -0.0001

Data Index: 318224 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2927. Min Act: -0.0001

Data Index: 815780 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2593. Min Act: -0.0001

Data Index: 54631 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2817. Min Act: -0.0001

Data Index: 731419 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2815. Min Act: -0.0001

Data Index: 76856 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2800. Min Act: -0.0001

Data Index: 154545 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2499. Min Act: -0.0001

Data Index: 821396 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2905. Min Act: -0.0001

Data Index: 646224 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2758. Min Act: -0.0001

Data Index: 846321 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2576. Min Act: -0.0001

Data Index: 1125163 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2665. Min Act: -0.0001

Data Index: 464907 (C4 (Web Text))

Max Activating Token Index: 32