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

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

Neuron 1856 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.5830. Min Act: -0.0000

Data Index: 48471 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.5403. Min Act: -0.0000

Data Index: 684306 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.5574. Min Act: -0.0000

Data Index: 539854 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.5328. Min Act: -0.0000

Data Index: 1135468 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.5219. Min Act: -0.0000

Data Index: 367981 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4997. Min Act: -0.0000

Data Index: 852654 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.5213. Min Act: -0.0000

Data Index: 384568 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4938. Min Act: -0.0000

Data Index: 900831 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4872. Min Act: -0.0000

Data Index: 1244084 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4807. Min Act: -0.0000

Data Index: 213205 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4614. Min Act: -0.0000

Data Index: 4274 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4772. Min Act: -0.0000

Data Index: 195588 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4616. Min Act: -0.0000

Data Index: 367662 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4806. Min Act: -0.0000

Data Index: 1058035 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4479. Min Act: -0.0000

Data Index: 53333 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4635. Min Act: -0.0000

Data Index: 157127 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4460. Min Act: -0.0000

Data Index: 484370 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4903. Min Act: -0.0000

Data Index: 109709 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4683. Min Act: -0.0000

Data Index: 878188 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4550. Min Act: -0.0000

Data Index: 206135 (C4 (Web Text))

Max Activating Token Index: 161