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

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

Neuron 1902 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.2150. Min Act: -0.0001

Data Index: 776050 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.2049. Min Act: -0.0001

Data Index: 1005389 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1261. Min Act: -0.0001

Data Index: 654435 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.0951. Min Act: -0.0001

Data Index: 1223304 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.0924. Min Act: -0.0001

Data Index: 307059 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.0525. Min Act: -0.0001

Data Index: 997284 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.0683. Min Act: -0.0001

Data Index: 856862 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.0738. Min Act: -0.0001

Data Index: 76384 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.0528. Min Act: -0.0001

Data Index: 836882 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.0578. Min Act: -0.0001

Data Index: 779350 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.0531. Min Act: -0.0001

Data Index: 474398 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.0456. Min Act: -0.0001

Data Index: 897824 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.0469. Min Act: -0.0001

Data Index: 1270098 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.0499. Min Act: -0.0001

Data Index: 1428452 (Python Code)

Max Activating Token Index: 62

Text #14

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.0476. Min Act: -0.0001

Data Index: 1185166 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.0450. Min Act: -0.0001

Data Index: 861840 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.0468. Min Act: -0.0001

Data Index: 232595 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.0501. Min Act: -0.0001

Data Index: 265398 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.0436. Min Act: -0.0001

Data Index: 567587 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.0398. Min Act: -0.0001

Data Index: 428685 (C4 (Web Text))

Max Activating Token Index: 829