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

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

Neuron 515 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: 0.5667. Min Range: -0.5667

Max Act: 0.5667. Min Act: -0.0000

Data Index: 580739 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4408. Min Act: -0.0000

Data Index: 1154931 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.3670. Min Act: -0.0000

Data Index: 974534 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.3697. Min Act: -0.0000

Data Index: 221382 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.3349. Min Act: -0.0000

Data Index: 16360 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.3332. Min Act: -0.0000

Data Index: 1123121 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.3305. Min Act: -0.0000

Data Index: 105153 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.3384. Min Act: -0.0000

Data Index: 939709 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.3278. Min Act: -0.0000

Data Index: 556110 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.3433. Min Act: -0.0000

Data Index: 1111891 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.3193. Min Act: -0.0000

Data Index: 51825 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.3212. Min Act: -0.0000

Data Index: 913978 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.3107. Min Act: -0.0000

Data Index: 49469 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.3208. Min Act: -0.0000

Data Index: 615421 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.3271. Min Act: -0.0000

Data Index: 1234892 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.3361. Min Act: -0.0000

Data Index: 1306658 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.3322. Min Act: -0.0000

Data Index: 661499 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.3198. Min Act: -0.0000

Data Index: 1115637 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.3217. Min Act: -0.0000

Data Index: 659389 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.3163. Min Act: -0.0000

Data Index: 615906 (C4 (Web Text))

Max Activating Token Index: 445