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

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

Neuron 4804 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5645. Min Range: -2.5645

Max Act: 2.3461. Min Act: -0.0000

Data Index: 829632 (C4 (Web Text))

Max Activating Token Index: 617

Text #1

Max Range: 2.5645. Min Range: -2.5645

Max Act: 2.5645. Min Act: -0.0000

Data Index: 1357031 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 2.5645. Min Range: -2.5645

Max Act: 2.4539. Min Act: -0.0001

Data Index: 267105 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 2.5645. Min Range: -2.5645

Max Act: 2.1998. Min Act: -0.0001

Data Index: 178473 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 2.5645. Min Range: -2.5645

Max Act: 2.1066. Min Act: -0.0000

Data Index: 1034489 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 2.5645. Min Range: -2.5645

Max Act: 2.0818. Min Act: -0.0000

Data Index: 323214 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 2.5645. Min Range: -2.5645

Max Act: 2.0543. Min Act: -0.0000

Data Index: 853028 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 2.5645. Min Range: -2.5645

Max Act: 1.8922. Min Act: -0.0000

Data Index: 344036 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 2.5645. Min Range: -2.5645

Max Act: 2.1443. Min Act: -0.0001

Data Index: 321176 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 2.5645. Min Range: -2.5645

Max Act: 2.0730. Min Act: -0.0001

Data Index: 1245357 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 2.5645. Min Range: -2.5645

Max Act: 2.0204. Min Act: -0.0000

Data Index: 521042 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 2.5645. Min Range: -2.5645

Max Act: 1.9423. Min Act: -0.0001

Data Index: 673494 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 2.5645. Min Range: -2.5645

Max Act: 1.9870. Min Act: -0.0001

Data Index: 1278870 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 2.5645. Min Range: -2.5645

Max Act: 2.0109. Min Act: -0.0000

Data Index: 646848 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 2.5645. Min Range: -2.5645

Max Act: 2.0365. Min Act: -0.0000

Data Index: 70704 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 2.5645. Min Range: -2.5645

Max Act: 2.0911. Min Act: -0.0001

Data Index: 1148197 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 2.5645. Min Range: -2.5645

Max Act: 2.1576. Min Act: -0.0001

Data Index: 381298 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 2.5645. Min Range: -2.5645

Max Act: 1.9149. Min Act: -0.0000

Data Index: 42939 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 2.5645. Min Range: -2.5645

Max Act: 2.1407. Min Act: -0.0000

Data Index: 996230 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 2.5645. Min Range: -2.5645

Max Act: 2.1218. Min Act: -0.0000

Data Index: 878972 (C4 (Web Text))

Max Activating Token Index: 989