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

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

Neuron 4860 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: 0.3055. Min Range: -0.3055

Max Act: 0.3022. Min Act: -0.0000

Data Index: 556962 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 0.3055. Min Range: -0.3055

Max Act: 0.2985. Min Act: -0.0000

Data Index: 1328990 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 0.3055. Min Range: -0.3055

Max Act: 0.3055. Min Act: -0.0000

Data Index: 787654 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 0.3055. Min Range: -0.3055

Max Act: 0.2875. Min Act: -0.0000

Data Index: 115535 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 0.3055. Min Range: -0.3055

Max Act: 0.2841. Min Act: -0.0000

Data Index: 332222 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 0.3055. Min Range: -0.3055

Max Act: 0.2918. Min Act: -0.0000

Data Index: 971871 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 0.3055. Min Range: -0.3055

Max Act: 0.2998. Min Act: -0.0000

Data Index: 397999 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 0.3055. Min Range: -0.3055

Max Act: 0.2775. Min Act: -0.0000

Data Index: 241757 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 0.3055. Min Range: -0.3055

Max Act: 0.2622. Min Act: -0.0000

Data Index: 131162 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 0.3055. Min Range: -0.3055

Max Act: 0.2572. Min Act: -0.0000

Data Index: 503831 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 0.3055. Min Range: -0.3055

Max Act: 0.2506. Min Act: -0.0000

Data Index: 771670 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.3055. Min Range: -0.3055

Max Act: 0.2598. Min Act: -0.0000

Data Index: 316588 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 0.3055. Min Range: -0.3055

Max Act: 0.2290. Min Act: -0.0000

Data Index: 1198414 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 0.3055. Min Range: -0.3055

Max Act: 0.2612. Min Act: -0.0000

Data Index: 426850 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 0.3055. Min Range: -0.3055

Max Act: 0.2712. Min Act: -0.0000

Data Index: 1343260 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 0.3055. Min Range: -0.3055

Max Act: 0.2634. Min Act: -0.0000

Data Index: 790521 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 0.3055. Min Range: -0.3055

Max Act: 0.2543. Min Act: -0.0000

Data Index: 1287659 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 0.3055. Min Range: -0.3055

Max Act: 0.2521. Min Act: -0.0000

Data Index: 720013 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 0.3055. Min Range: -0.3055

Max Act: 0.2492. Min Act: -0.0000

Data Index: 31011 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 0.3055. Min Range: -0.3055

Max Act: 0.2475. Min Act: -0.0000

Data Index: 366943 (C4 (Web Text))

Max Activating Token Index: 633