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

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

Neuron 348 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: 0.3455. Min Range: -0.3455

Max Act: 0.3455. Min Act: -0.0001

Data Index: 494132 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.3275. Min Act: -0.0001

Data Index: 427853 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.3366. Min Act: -0.0001

Data Index: 872431 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.3142. Min Act: -0.0001

Data Index: 937444 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.3232. Min Act: -0.0001

Data Index: 639474 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.3452. Min Act: -0.0000

Data Index: 1263666 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.3346. Min Act: -0.0000

Data Index: 281644 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.3010. Min Act: -0.0000

Data Index: 908495 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.3026. Min Act: -0.0001

Data Index: 1212455 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.3212. Min Act: -0.0001

Data Index: 121267 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.3112. Min Act: -0.0000

Data Index: 337953 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.3162. Min Act: -0.0000

Data Index: 550573 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2864. Min Act: -0.0000

Data Index: 183991 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.3158. Min Act: -0.0001

Data Index: 625631 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.3137. Min Act: -0.0000

Data Index: 63757 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.3030. Min Act: -0.0000

Data Index: 811449 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.3144. Min Act: -0.0000

Data Index: 624136 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.3038. Min Act: -0.0000

Data Index: 508077 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.3120. Min Act: -0.0000

Data Index: 158576 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2729. Min Act: -0.0001

Data Index: 654269 (C4 (Web Text))

Max Activating Token Index: 832