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

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

Neuron 524 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: 0.9649. Min Range: -0.9649

Max Act: 0.9649. Min Act: -0.0001

Data Index: 236827 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.9183. Min Act: -0.0001

Data Index: 957354 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.8662. Min Act: -0.0001

Data Index: 716201 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.8876. Min Act: -0.0001

Data Index: 973634 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.8632. Min Act: -0.0001

Data Index: 773688 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.8528. Min Act: -0.0001

Data Index: 39405 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.8376. Min Act: -0.0001

Data Index: 407334 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.9069. Min Act: -0.0001

Data Index: 661241 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.7260. Min Act: -0.0001

Data Index: 177921 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.8493. Min Act: -0.0001

Data Index: 1189187 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.7593. Min Act: -0.0001

Data Index: 230349 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.7673. Min Act: -0.0001

Data Index: 472668 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.7965. Min Act: -0.0001

Data Index: 51834 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.7669. Min Act: -0.0001

Data Index: 675765 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.8169. Min Act: -0.0001

Data Index: 1269416 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.7554. Min Act: -0.0001

Data Index: 516062 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.7958. Min Act: -0.0001

Data Index: 791376 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.8007. Min Act: -0.0001

Data Index: 190220 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.7910. Min Act: -0.0001

Data Index: 560554 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.7536. Min Act: -0.0001

Data Index: 1167094 (C4 (Web Text))

Max Activating Token Index: 982