Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 767 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3394. Min Range: -2.3394

Max Act: 2.3394. Min Act: -0.0000

Data Index: 1590314 (Python Code)

Max Activating Token Index: 205

Text #1

Max Range: 2.3394. Min Range: -2.3394

Max Act: 2.2423. Min Act: -0.0000

Data Index: 1394490 (Python Code)

Max Activating Token Index: 866

Text #2

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.9300. Min Act: -0.0000

Data Index: 1653045 (Python Code)

Max Activating Token Index: 756

Text #3

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.9171. Min Act: -0.0000

Data Index: 1214475 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.6670. Min Act: -0.0000

Data Index: 1060427 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.6941. Min Act: -0.0000

Data Index: 793016 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.6229. Min Act: 0.0000

Data Index: 341581 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.7372. Min Act: -0.0000

Data Index: 1202114 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.5689. Min Act: 0.0001

Data Index: 207227 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.5421. Min Act: 0.0000

Data Index: 1338953 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.4181. Min Act: -0.0000

Data Index: 990871 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.4370. Min Act: -0.0000

Data Index: 381766 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.3721. Min Act: -0.0000

Data Index: 127021 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.4477. Min Act: -0.0000

Data Index: 1425599 (Python Code)

Max Activating Token Index: 426

Text #14

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.4062. Min Act: -0.0000

Data Index: 1436036 (Python Code)

Max Activating Token Index: 615

Text #15

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.3700. Min Act: -0.0000

Data Index: 371562 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.2782. Min Act: -0.0000

Data Index: 873699 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.3408. Min Act: 0.0000

Data Index: 1282976 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.3081. Min Act: -0.0000

Data Index: 1209189 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.2593. Min Act: 0.0000

Data Index: 1005617 (C4 (Web Text))

Max Activating Token Index: 486