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

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

Neuron 2105 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.5549. Min Act: -0.0001

Data Index: 636525 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.5490. Min Act: -0.0001

Data Index: 37633 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.5174. Min Act: -0.0001

Data Index: 610598 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.5147. Min Act: -0.0001

Data Index: 769673 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.4957. Min Act: -0.0001

Data Index: 834698 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.4557. Min Act: -0.0001

Data Index: 234690 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.4712. Min Act: -0.0001

Data Index: 454115 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.4686. Min Act: -0.0001

Data Index: 1536906 (Python Code)

Max Activating Token Index: 69

Text #8

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.4688. Min Act: -0.0001

Data Index: 1195131 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.4667. Min Act: -0.0001

Data Index: 409979 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.4612. Min Act: -0.0001

Data Index: 1611424 (Python Code)

Max Activating Token Index: 716

Text #11

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.4740. Min Act: -0.0001

Data Index: 736481 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.4385. Min Act: -0.0001

Data Index: 934402 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.4348. Min Act: -0.0001

Data Index: 396107 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.4847. Min Act: -0.0001

Data Index: 1292915 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.5023. Min Act: -0.0001

Data Index: 18811 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.4178. Min Act: -0.0001

Data Index: 1273594 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.4273. Min Act: -0.0001

Data Index: 1500994 (Python Code)

Max Activating Token Index: 159

Text #18

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.4383. Min Act: -0.0001

Data Index: 620511 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.4197. Min Act: -0.0001

Data Index: 208047 (C4 (Web Text))

Max Activating Token Index: 319