Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3950 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.9956. Min Act: -0.0001

Data Index: 128458 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.9118. Min Act: -0.0000

Data Index: 635402 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.7965. Min Act: -0.0001

Data Index: 1291861 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.8917. Min Act: -0.0000

Data Index: 1094771 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.7809. Min Act: -0.0000

Data Index: 344801 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.7664. Min Act: -0.0000

Data Index: 329168 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.7307. Min Act: -0.0001

Data Index: 992595 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.7543. Min Act: -0.0000

Data Index: 1339676 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.7549. Min Act: -0.0000

Data Index: 214996 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.7099. Min Act: -0.0001

Data Index: 971952 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.7037. Min Act: -0.0000

Data Index: 1145150 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1307653 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.6806. Min Act: -0.0000

Data Index: 787669 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.6834. Min Act: -0.0001

Data Index: 681559 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.6261. Min Act: -0.0000

Data Index: 338625 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.6278. Min Act: -0.0000

Data Index: 312389 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.7295. Min Act: -0.0000

Data Index: 932279 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.6757. Min Act: -0.0000

Data Index: 384097 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.6756. Min Act: -0.0000

Data Index: 239457 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.6212. Min Act: -0.0001

Data Index: 1093148 (C4 (Web Text))

Max Activating Token Index: 70