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

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

Neuron 3673 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.2784. Min Range: -6.2784

Max Act: 6.2784. Min Act: -0.0000

Data Index: 66059 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 6.2784. Min Range: -6.2784

Max Act: 6.2517. Min Act: 0.0000

Data Index: 747561 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 6.2784. Min Range: -6.2784

Max Act: 5.8480. Min Act: 0.0002

Data Index: 119879 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 6.2784. Min Range: -6.2784

Max Act: 6.1275. Min Act: -0.0000

Data Index: 1350238 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 6.2784. Min Range: -6.2784

Max Act: 5.7110. Min Act: 0.0000

Data Index: 481177 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 6.2784. Min Range: -6.2784

Max Act: 5.8678. Min Act: 0.0001

Data Index: 959511 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 6.2784. Min Range: -6.2784

Max Act: 5.8496. Min Act: -0.0000

Data Index: 758316 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 6.2784. Min Range: -6.2784

Max Act: 5.8371. Min Act: -0.0000

Data Index: 571797 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 6.2784. Min Range: -6.2784

Max Act: 5.9636. Min Act: -0.0000

Data Index: 770837 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 6.2784. Min Range: -6.2784

Max Act: 5.5585. Min Act: -0.0000

Data Index: 1104323 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 6.2784. Min Range: -6.2784

Max Act: 5.7254. Min Act: -0.0000

Data Index: 1185372 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 6.2784. Min Range: -6.2784

Max Act: 5.6802. Min Act: 0.0001

Data Index: 445980 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 6.2784. Min Range: -6.2784

Max Act: 6.0374. Min Act: 0.0000

Data Index: 657783 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 6.2784. Min Range: -6.2784

Max Act: 5.6253. Min Act: 0.0000

Data Index: 878086 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 6.2784. Min Range: -6.2784

Max Act: 5.7722. Min Act: 0.0000

Data Index: 54582 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 6.2784. Min Range: -6.2784

Max Act: 5.5532. Min Act: 0.0000

Data Index: 299876 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 6.2784. Min Range: -6.2784

Max Act: 5.3460. Min Act: 0.0000

Data Index: 101870 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 6.2784. Min Range: -6.2784

Max Act: 5.4855. Min Act: 0.0000

Data Index: 278141 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 6.2784. Min Range: -6.2784

Max Act: 5.4397. Min Act: 0.0000

Data Index: 644747 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 6.2784. Min Range: -6.2784

Max Act: 5.5609. Min Act: 0.0000

Data Index: 421907 (C4 (Web Text))

Max Activating Token Index: 483