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

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

Neuron 5780 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 13.5305. Min Range: -13.5305

Max Act: 13.5305. Min Act: -0.0000

Data Index: 1040685 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 13.5305. Min Range: -13.5305

Max Act: 4.3633. Min Act: -0.0000

Data Index: 1109101 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 13.5305. Min Range: -13.5305

Max Act: 0.1406. Min Act: -0.0000

Data Index: 826236 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 13.5305. Min Range: -13.5305

Max Act: 0.6132. Min Act: -0.0000

Data Index: 812515 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 13.5305. Min Range: -13.5305

Max Act: 0.5448. Min Act: -0.0000

Data Index: 442568 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 13.5305. Min Range: -13.5305

Max Act: 0.0279. Min Act: -0.0000

Data Index: 1051036 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 13.5305. Min Range: -13.5305

Max Act: 0.4187. Min Act: -0.0000

Data Index: 1035408 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 13.5305. Min Range: -13.5305

Max Act: 0.3906. Min Act: -0.0000

Data Index: 563580 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 13.5305. Min Range: -13.5305

Max Act: 0.3588. Min Act: -0.0000

Data Index: 821213 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 13.5305. Min Range: -13.5305

Max Act: 0.3882. Min Act: -0.0000

Data Index: 350818 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 13.5305. Min Range: -13.5305

Max Act: 0.3481. Min Act: -0.0000

Data Index: 1275136 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 13.5305. Min Range: -13.5305

Max Act: 0.3691. Min Act: -0.0000

Data Index: 249561 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 13.5305. Min Range: -13.5305

Max Act: 0.3906. Min Act: -0.0000

Data Index: 42022 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 13.5305. Min Range: -13.5305

Max Act: 0.4168. Min Act: -0.0000

Data Index: 1078040 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 13.5305. Min Range: -13.5305

Max Act: 0.3193. Min Act: -0.0000

Data Index: 667275 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 13.5305. Min Range: -13.5305

Max Act: 0.3448. Min Act: -0.0000

Data Index: 1144902 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 13.5305. Min Range: -13.5305

Max Act: 0.3577. Min Act: -0.0000

Data Index: 1186885 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 13.5305. Min Range: -13.5305

Max Act: 0.3279. Min Act: -0.0000

Data Index: 321747 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 13.5305. Min Range: -13.5305

Max Act: 0.4055. Min Act: -0.0000

Data Index: 766855 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 13.5305. Min Range: -13.5305

Max Act: 0.3206. Min Act: -0.0000

Data Index: 787552 (C4 (Web Text))

Max Activating Token Index: 516