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

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

Neuron 4541 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.3574. Min Act: -0.0000

Data Index: 801774 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.3123. Min Act: -0.0000

Data Index: 1254329 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.3316. Min Act: -0.0000

Data Index: 1233438 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2990. Min Act: -0.0000

Data Index: 948811 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2952. Min Act: 0.0000

Data Index: 959244 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2994. Min Act: -0.0000

Data Index: 688976 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2945. Min Act: -0.0000

Data Index: 794905 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2928. Min Act: 0.0000

Data Index: 88051 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2643. Min Act: 0.0000

Data Index: 1145970 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2875. Min Act: -0.0000

Data Index: 923118 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2738. Min Act: -0.0000

Data Index: 825087 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2668. Min Act: -0.0000

Data Index: 728949 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2768. Min Act: -0.0000

Data Index: 1024757 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2743. Min Act: -0.0000

Data Index: 1417083 (Python Code)

Max Activating Token Index: 426

Text #14

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2526. Min Act: -0.0000

Data Index: 560535 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2601. Min Act: -0.0000

Data Index: 991634 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2554. Min Act: -0.0000

Data Index: 965486 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2543. Min Act: -0.0000

Data Index: 1236121 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2495. Min Act: -0.0000

Data Index: 988619 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2227. Min Act: 0.0000

Data Index: 586358 (C4 (Web Text))

Max Activating Token Index: 754