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

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

Neuron 641 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2956. Min Act: -0.0000

Data Index: 172247 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2865. Min Act: -0.0001

Data Index: 950957 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2573. Min Act: -0.0001

Data Index: 730110 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2648. Min Act: -0.0000

Data Index: 1242552 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2571. Min Act: -0.0000

Data Index: 1307884 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2598. Min Act: -0.0000

Data Index: 1105383 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2608. Min Act: -0.0001

Data Index: 393568 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2495. Min Act: -0.0000

Data Index: 416854 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2548. Min Act: -0.0000

Data Index: 215405 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2553. Min Act: -0.0000

Data Index: 589094 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2380. Min Act: -0.0000

Data Index: 621460 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2245. Min Act: -0.0001

Data Index: 888506 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2075. Min Act: -0.0000

Data Index: 186794 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2088. Min Act: -0.0000

Data Index: 730516 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2217. Min Act: -0.0000

Data Index: 290264 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2148. Min Act: -0.0001

Data Index: 409571 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2045. Min Act: -0.0001

Data Index: 943726 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.1985. Min Act: -0.0000

Data Index: 1185157 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.1909. Min Act: -0.0001

Data Index: 449362 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2034. Min Act: -0.0000

Data Index: 850788 (C4 (Web Text))

Max Activating Token Index: 220