Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2536 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.3640. Min Act: -0.0000

Data Index: 878485 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.3279. Min Act: -0.0000

Data Index: 353703 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.3469. Min Act: -0.0000

Data Index: 629902 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.3119. Min Act: -0.0000

Data Index: 1340937 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2973. Min Act: -0.0000

Data Index: 942872 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2875. Min Act: -0.0000

Data Index: 898254 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2903. Min Act: -0.0000

Data Index: 116173 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2938. Min Act: -0.0000

Data Index: 995050 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2775. Min Act: -0.0000

Data Index: 675405 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2805. Min Act: -0.0000

Data Index: 41260 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2863. Min Act: -0.0000

Data Index: 456482 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2555. Min Act: -0.0000

Data Index: 415500 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2726. Min Act: -0.0000

Data Index: 814460 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2656. Min Act: -0.0000

Data Index: 1112418 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2484. Min Act: -0.0000

Data Index: 892830 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2667. Min Act: -0.0000

Data Index: 1217921 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2567. Min Act: -0.0000

Data Index: 289809 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2636. Min Act: -0.0000

Data Index: 1139658 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2427. Min Act: -0.0000

Data Index: 263016 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2627. Min Act: -0.0000

Data Index: 779571 (C4 (Web Text))

Max Activating Token Index: 145