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

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

Neuron 4616 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: 0.3895. Min Range: -0.3895

Max Act: 0.3895. Min Act: -0.0001

Data Index: 76508 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3412. Min Act: -0.0001

Data Index: 102925 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3461. Min Act: -0.0001

Data Index: 836492 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3371. Min Act: -0.0001

Data Index: 778512 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3350. Min Act: -0.0001

Data Index: 551541 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3344. Min Act: -0.0001

Data Index: 1120625 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3353. Min Act: -0.0001

Data Index: 1086563 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2967. Min Act: -0.0001

Data Index: 694838 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3090. Min Act: -0.0001

Data Index: 423028 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3197. Min Act: -0.0001

Data Index: 896749 (C4 (Web Text))

Max Activating Token Index: 374

Text #10

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3354. Min Act: -0.0001

Data Index: 49659 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3164. Min Act: -0.0001

Data Index: 730787 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3141. Min Act: -0.0001

Data Index: 1103934 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3349. Min Act: -0.0001

Data Index: 1159882 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3134. Min Act: -0.0001

Data Index: 440021 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3108. Min Act: -0.0001

Data Index: 594197 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3208. Min Act: -0.0001

Data Index: 601849 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3065. Min Act: -0.0001

Data Index: 1219659 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3091. Min Act: -0.0001

Data Index: 625384 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3273. Min Act: -0.0001

Data Index: 1104744 (C4 (Web Text))

Max Activating Token Index: 566