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

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

Neuron 2442 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.2602. Min Act: -0.0001

Data Index: 1373832 (Python Code)

Max Activating Token Index: 244

Text #1

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.2548. Min Act: -0.0001

Data Index: 1554012 (Python Code)

Max Activating Token Index: 89

Text #2

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.1907. Min Act: -0.0001

Data Index: 1464671 (Python Code)

Max Activating Token Index: 398

Text #3

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.2439. Min Act: -0.0001

Data Index: 1597660 (Python Code)

Max Activating Token Index: 687

Text #4

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.1978. Min Act: -0.0001

Data Index: 1380062 (Python Code)

Max Activating Token Index: 135

Text #5

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.1937. Min Act: -0.0001

Data Index: 1635600 (Python Code)

Max Activating Token Index: 142

Text #6

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.1266. Min Act: -0.0001

Data Index: 1362118 (Python Code)

Max Activating Token Index: 485

Text #7

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.1235. Min Act: -0.0001

Data Index: 1518431 (Python Code)

Max Activating Token Index: 975

Text #8

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.0322. Min Act: -0.0001

Data Index: 1440621 (Python Code)

Max Activating Token Index: 546

Text #9

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.0598. Min Act: -0.0001

Data Index: 1608347 (Python Code)

Max Activating Token Index: 102

Text #10

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.0808. Min Act: -0.0001

Data Index: 1437477 (Python Code)

Max Activating Token Index: 1007

Text #11

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.0333. Min Act: -0.0001

Data Index: 1384361 (Python Code)

Max Activating Token Index: 523

Text #12

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.0352. Min Act: -0.0001

Data Index: 1572347 (Python Code)

Max Activating Token Index: 934

Text #13

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.0488. Min Act: -0.0001

Data Index: 1611180 (Python Code)

Max Activating Token Index: 189

Text #14

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.0138. Min Act: -0.0001

Data Index: 1407124 (Python Code)

Max Activating Token Index: 193

Text #15

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.0107. Min Act: -0.0001

Data Index: 1512214 (Python Code)

Max Activating Token Index: 221

Text #16

Max Range: 1.2602. Min Range: -1.2602

Max Act: 0.9991. Min Act: -0.0001

Data Index: 1485526 (Python Code)

Max Activating Token Index: 132

Text #17

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.0439. Min Act: -0.0001

Data Index: 1560018 (Python Code)

Max Activating Token Index: 90

Text #18

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.0141. Min Act: -0.0001

Data Index: 1522262 (Python Code)

Max Activating Token Index: 941

Text #19

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.0046. Min Act: -0.0001

Data Index: 1503554 (Python Code)

Max Activating Token Index: 255