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

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

Neuron 5522 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.3872. Min Act: -0.0002

Data Index: 1612628 (Python Code)

Max Activating Token Index: 202

Text #1

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.3363. Min Act: -0.0002

Data Index: 1593804 (Python Code)

Max Activating Token Index: 408

Text #2

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.3251. Min Act: -0.0002

Data Index: 1363491 (Python Code)

Max Activating Token Index: 209

Text #3

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.3168. Min Act: -0.0002

Data Index: 1501180 (Python Code)

Max Activating Token Index: 61

Text #4

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2933. Min Act: -0.0002

Data Index: 1574682 (Python Code)

Max Activating Token Index: 803

Text #5

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2899. Min Act: -0.0002

Data Index: 1452069 (Python Code)

Max Activating Token Index: 962

Text #6

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2980. Min Act: -0.0002

Data Index: 1462189 (Python Code)

Max Activating Token Index: 834

Text #7

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.3075. Min Act: -0.0002

Data Index: 1430056 (Python Code)

Max Activating Token Index: 84

Text #8

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.3131. Min Act: -0.0002

Data Index: 1525928 (Python Code)

Max Activating Token Index: 796

Text #9

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2831. Min Act: -0.0002

Data Index: 1388004 (Python Code)

Max Activating Token Index: 155

Text #10

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2770. Min Act: -0.0002

Data Index: 1370157 (Python Code)

Max Activating Token Index: 263

Text #11

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2802. Min Act: -0.0002

Data Index: 1022137 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2854. Min Act: -0.0002

Data Index: 1488096 (Python Code)

Max Activating Token Index: 967

Text #13

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2657. Min Act: -0.0002

Data Index: 1561971 (Python Code)

Max Activating Token Index: 979

Text #14

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2467. Min Act: -0.0002

Data Index: 1010229 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2593. Min Act: -0.0002

Data Index: 1365126 (Python Code)

Max Activating Token Index: 852

Text #16

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2533. Min Act: -0.0002

Data Index: 247702 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2450. Min Act: -0.0002

Data Index: 1270202 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2528. Min Act: -0.0002

Data Index: 1289828 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2621. Min Act: -0.0002

Data Index: 1389012 (Python Code)

Max Activating Token Index: 241