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

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

Neuron 3154 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0515. Min Range: -2.0515

Max Act: 2.0515. Min Act: -0.0000

Data Index: 849858 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 2.0515. Min Range: -2.0515

Max Act: 1.7572. Min Act: -0.0000

Data Index: 1142494 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 2.0515. Min Range: -2.0515

Max Act: 1.6096. Min Act: -0.0000

Data Index: 248964 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 2.0515. Min Range: -2.0515

Max Act: 1.4571. Min Act: -0.0000

Data Index: 1154032 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 2.0515. Min Range: -2.0515

Max Act: 1.5390. Min Act: -0.0000

Data Index: 130598 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 2.0515. Min Range: -2.0515

Max Act: 1.5098. Min Act: -0.0000

Data Index: 1032138 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 2.0515. Min Range: -2.0515

Max Act: 1.4645. Min Act: 0.0000

Data Index: 1255947 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 2.0515. Min Range: -2.0515

Max Act: 1.3736. Min Act: -0.0000

Data Index: 1063948 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 2.0515. Min Range: -2.0515

Max Act: 1.4474. Min Act: -0.0000

Data Index: 992508 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 2.0515. Min Range: -2.0515

Max Act: 1.4528. Min Act: -0.0000

Data Index: 257950 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 2.0515. Min Range: -2.0515

Max Act: 1.3480. Min Act: -0.0000

Data Index: 621480 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 2.0515. Min Range: -2.0515

Max Act: 1.4375. Min Act: -0.0000

Data Index: 1306885 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 2.0515. Min Range: -2.0515

Max Act: 1.3443. Min Act: -0.0000

Data Index: 602655 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 2.0515. Min Range: -2.0515

Max Act: 1.3943. Min Act: -0.0000

Data Index: 451123 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 2.0515. Min Range: -2.0515

Max Act: 1.3563. Min Act: -0.0000

Data Index: 1128859 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 2.0515. Min Range: -2.0515

Max Act: 1.3087. Min Act: -0.0000

Data Index: 894026 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 2.0515. Min Range: -2.0515

Max Act: 1.3333. Min Act: -0.0000

Data Index: 1352072 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 2.0515. Min Range: -2.0515

Max Act: 1.2467. Min Act: -0.0000

Data Index: 624070 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 2.0515. Min Range: -2.0515

Max Act: 1.4011. Min Act: -0.0000

Data Index: 932063 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 2.0515. Min Range: -2.0515

Max Act: 1.2932. Min Act: -0.0000

Data Index: 463697 (C4 (Web Text))

Max Activating Token Index: 835