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

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

Neuron 813 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.5105. Min Act: -0.0001

Data Index: 935976 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4868. Min Act: -0.0001

Data Index: 739573 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.5025. Min Act: -0.0001

Data Index: 753542 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4845. Min Act: -0.0001

Data Index: 1110616 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4822. Min Act: -0.0001

Data Index: 860561 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4478. Min Act: -0.0001

Data Index: 313283 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4445. Min Act: -0.0001

Data Index: 720650 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4449. Min Act: -0.0001

Data Index: 748479 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4408. Min Act: -0.0001

Data Index: 674873 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4112. Min Act: -0.0001

Data Index: 412375 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4336. Min Act: -0.0001

Data Index: 1016006 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4441. Min Act: -0.0001

Data Index: 1132599 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4251. Min Act: -0.0001

Data Index: 714674 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4137. Min Act: -0.0001

Data Index: 1332741 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4208. Min Act: -0.0001

Data Index: 320097 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4096. Min Act: -0.0001

Data Index: 103593 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4069. Min Act: -0.0001

Data Index: 127059 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4189. Min Act: -0.0001

Data Index: 97967 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.3886. Min Act: -0.0001

Data Index: 950546 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4145. Min Act: -0.0001

Data Index: 1290392 (C4 (Web Text))

Max Activating Token Index: 652