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

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

Neuron 3152 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3925. Min Act: -0.0001

Data Index: 758351 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2969. Min Act: -0.0001

Data Index: 970674 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2760. Min Act: -0.0001

Data Index: 848012 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2738. Min Act: -0.0001

Data Index: 108515 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2667. Min Act: -0.0001

Data Index: 731200 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2789. Min Act: -0.0001

Data Index: 781021 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2743. Min Act: -0.0001

Data Index: 820723 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2740. Min Act: -0.0001

Data Index: 1199055 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2815. Min Act: -0.0001

Data Index: 221634 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2806. Min Act: -0.0001

Data Index: 1312889 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2772. Min Act: -0.0001

Data Index: 1007271 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2680. Min Act: -0.0001

Data Index: 1078059 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2653. Min Act: -0.0001

Data Index: 670385 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2663. Min Act: -0.0001

Data Index: 1123438 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2747. Min Act: -0.0001

Data Index: 734723 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2643. Min Act: -0.0001

Data Index: 197211 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2827. Min Act: -0.0001

Data Index: 995048 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2640. Min Act: -0.0001

Data Index: 626810 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2489. Min Act: -0.0001

Data Index: 1253138 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2479. Min Act: -0.0001

Data Index: 30076 (C4 (Web Text))

Max Activating Token Index: 464