Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 583 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4994. Min Range: -1.4994

Max Act: 1.4994. Min Act: -0.0000

Data Index: 141320 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 1.4994. Min Range: -1.4994

Max Act: 1.4765. Min Act: -0.0001

Data Index: 515979 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 1.4994. Min Range: -1.4994

Max Act: 1.3905. Min Act: -0.0001

Data Index: 177153 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 1.4994. Min Range: -1.4994

Max Act: 1.3408. Min Act: -0.0001

Data Index: 1270171 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 1.4994. Min Range: -1.4994

Max Act: 1.3426. Min Act: -0.0000

Data Index: 1116107 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 1.4994. Min Range: -1.4994

Max Act: 1.2955. Min Act: -0.0000

Data Index: 1223865 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 1.4994. Min Range: -1.4994

Max Act: 1.3039. Min Act: -0.0001

Data Index: 483778 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 1.4994. Min Range: -1.4994

Max Act: 1.2987. Min Act: -0.0001

Data Index: 1638214 (Python Code)

Max Activating Token Index: 142

Text #8

Max Range: 1.4994. Min Range: -1.4994

Max Act: 1.2966. Min Act: -0.0000

Data Index: 847061 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 1.4994. Min Range: -1.4994

Max Act: 1.3315. Min Act: -0.0000

Data Index: 222998 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 1.4994. Min Range: -1.4994

Max Act: 1.2409. Min Act: -0.0000

Data Index: 1264807 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 1.4994. Min Range: -1.4994

Max Act: 1.2590. Min Act: -0.0001

Data Index: 773779 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 1.4994. Min Range: -1.4994

Max Act: 1.2689. Min Act: -0.0001

Data Index: 909074 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 1.4994. Min Range: -1.4994

Max Act: 1.2135. Min Act: -0.0001

Data Index: 1410778 (Python Code)

Max Activating Token Index: 343

Text #14

Max Range: 1.4994. Min Range: -1.4994

Max Act: 1.2457. Min Act: -0.0000

Data Index: 502943 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 1.4994. Min Range: -1.4994

Max Act: 1.3061. Min Act: -0.0001

Data Index: 171056 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 1.4994. Min Range: -1.4994

Max Act: 1.3292. Min Act: -0.0001

Data Index: 1251825 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 1.4994. Min Range: -1.4994

Max Act: 1.2386. Min Act: -0.0001

Data Index: 1299811 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 1.4994. Min Range: -1.4994

Max Act: 1.2993. Min Act: -0.0000

Data Index: 382434 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 1.4994. Min Range: -1.4994

Max Act: 1.2237. Min Act: -0.0000

Data Index: 667535 (C4 (Web Text))

Max Activating Token Index: 473