Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1520 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.4782. Min Act: -0.0001

Data Index: 15284 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.4336. Min Act: -0.0001

Data Index: 615530 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.4259. Min Act: -0.0001

Data Index: 708608 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.4073. Min Act: -0.0001

Data Index: 562427 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3836. Min Act: -0.0001

Data Index: 754921 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3599. Min Act: -0.0001

Data Index: 158614 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3846. Min Act: -0.0001

Data Index: 1116382 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3622. Min Act: -0.0001

Data Index: 14322 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3472. Min Act: -0.0001

Data Index: 475257 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3660. Min Act: -0.0001

Data Index: 1178997 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3689. Min Act: -0.0001

Data Index: 51169 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3714. Min Act: -0.0001

Data Index: 958790 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3493. Min Act: -0.0001

Data Index: 239883 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3310. Min Act: -0.0001

Data Index: 175736 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3597. Min Act: -0.0001

Data Index: 924442 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3012. Min Act: -0.0001

Data Index: 598650 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3206. Min Act: -0.0001

Data Index: 585676 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3435. Min Act: -0.0001

Data Index: 209573 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.2800. Min Act: -0.0001

Data Index: 1197582 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3293. Min Act: -0.0001

Data Index: 1120130 (C4 (Web Text))

Max Activating Token Index: 300