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

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

Neuron 1804 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4925. Min Act: -0.0000

Data Index: 1583399 (Python Code)

Max Activating Token Index: 962

Text #1

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4546. Min Act: -0.0000

Data Index: 1611181 (Python Code)

Max Activating Token Index: 1013

Text #2

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4494. Min Act: -0.0000

Data Index: 1537477 (Python Code)

Max Activating Token Index: 871

Text #3

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1360193 (Python Code)

Max Activating Token Index: 177

Text #4

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4459. Min Act: -0.0000

Data Index: 1590618 (Python Code)

Max Activating Token Index: 95

Text #5

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4381. Min Act: -0.0000

Data Index: 1576578 (Python Code)

Max Activating Token Index: 1019

Text #6

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4227. Min Act: -0.0000

Data Index: 1366088 (Python Code)

Max Activating Token Index: 926

Text #7

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4311. Min Act: -0.0000

Data Index: 1381544 (Python Code)

Max Activating Token Index: 876

Text #8

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4034. Min Act: -0.0000

Data Index: 1447713 (Python Code)

Max Activating Token Index: 225

Text #9

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4617. Min Act: -0.0000

Data Index: 1484078 (Python Code)

Max Activating Token Index: 672

Text #10

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4591. Min Act: -0.0000

Data Index: 1570752 (Python Code)

Max Activating Token Index: 73

Text #11

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4123. Min Act: -0.0000

Data Index: 1437934 (Python Code)

Max Activating Token Index: 761

Text #12

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4430. Min Act: -0.0000

Data Index: 1626807 (Python Code)

Max Activating Token Index: 893

Text #13

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4135. Min Act: -0.0000

Data Index: 1508974 (Python Code)

Max Activating Token Index: 74

Text #14

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4272. Min Act: -0.0000

Data Index: 1634072 (Python Code)

Max Activating Token Index: 1010

Text #15

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4091. Min Act: -0.0000

Data Index: 1583955 (Python Code)

Max Activating Token Index: 669

Text #16

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4059. Min Act: -0.0000

Data Index: 1564283 (Python Code)

Max Activating Token Index: 925

Text #17

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.3897. Min Act: -0.0000

Data Index: 1481718 (Python Code)

Max Activating Token Index: 129

Text #18

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4480. Min Act: -0.0000

Data Index: 1522422 (Python Code)

Max Activating Token Index: 938

Text #19

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4025. Min Act: -0.0000

Data Index: 1383295 (Python Code)

Max Activating Token Index: 975