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

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

Neuron 3355 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.4592. Min Act: -0.0001

Data Index: 675354 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.4599. Min Act: -0.0001

Data Index: 391111 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.4368. Min Act: -0.0001

Data Index: 1056313 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.4077. Min Act: -0.0001

Data Index: 186390 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.3871. Min Act: -0.0001

Data Index: 834200 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.3843. Min Act: -0.0001

Data Index: 1224199 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.3821. Min Act: -0.0001

Data Index: 946375 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.3450. Min Act: -0.0001

Data Index: 727151 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.3701. Min Act: -0.0001

Data Index: 731039 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.3670. Min Act: -0.0001

Data Index: 1249663 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.3509. Min Act: -0.0001

Data Index: 1135414 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.3613. Min Act: -0.0001

Data Index: 371315 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.3312. Min Act: -0.0001

Data Index: 1188008 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.3573. Min Act: -0.0001

Data Index: 448070 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.3315. Min Act: -0.0001

Data Index: 210969 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.3428. Min Act: -0.0001

Data Index: 350185 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.3364. Min Act: -0.0001

Data Index: 59735 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.3342. Min Act: -0.0001

Data Index: 865339 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.3211. Min Act: -0.0001

Data Index: 1244164 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.3314. Min Act: -0.0001

Data Index: 405788 (C4 (Web Text))

Max Activating Token Index: 490