Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3149 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.4987. Min Act: 0.0000

Data Index: 448875 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.4870. Min Act: -0.0000

Data Index: 1212022 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.4420. Min Act: -0.0000

Data Index: 53444 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3938. Min Act: 0.0000

Data Index: 30120 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3964. Min Act: 0.0000

Data Index: 119555 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3669. Min Act: 0.0000

Data Index: 976120 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3648. Min Act: -0.0000

Data Index: 738707 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3517. Min Act: -0.0000

Data Index: 125221 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3722. Min Act: 0.0000

Data Index: 1189184 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3585. Min Act: 0.0000

Data Index: 1150575 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3489. Min Act: 0.0000

Data Index: 854179 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3336. Min Act: 0.0000

Data Index: 139124 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3338. Min Act: -0.0000

Data Index: 1032054 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3422. Min Act: -0.0000

Data Index: 586057 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3397. Min Act: 0.0000

Data Index: 915383 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3182. Min Act: 0.0001

Data Index: 303935 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3184. Min Act: -0.0000

Data Index: 678149 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3160. Min Act: 0.0001

Data Index: 122044 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3059. Min Act: -0.0000

Data Index: 1294580 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3189. Min Act: 0.0000

Data Index: 1204814 (C4 (Web Text))

Max Activating Token Index: 335