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

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

Neuron 5060 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.5842. Min Act: -0.0000

Data Index: 628766 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.5339. Min Act: -0.0000

Data Index: 617466 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4870. Min Act: -0.0000

Data Index: 850654 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4963. Min Act: -0.0000

Data Index: 292837 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4576. Min Act: -0.0000

Data Index: 592517 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4982. Min Act: -0.0000

Data Index: 1296740 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4817. Min Act: -0.0000

Data Index: 456276 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4624. Min Act: -0.0000

Data Index: 271242 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4602. Min Act: -0.0000

Data Index: 1084331 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4539. Min Act: -0.0000

Data Index: 347921 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4547. Min Act: -0.0000

Data Index: 783828 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4646. Min Act: -0.0000

Data Index: 876507 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4497. Min Act: -0.0000

Data Index: 1257183 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4448. Min Act: -0.0000

Data Index: 1203588 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4483. Min Act: -0.0000

Data Index: 128084 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4329. Min Act: -0.0000

Data Index: 311367 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4442. Min Act: -0.0000

Data Index: 601152 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4431. Min Act: -0.0000

Data Index: 1219979 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4420. Min Act: -0.0000

Data Index: 213034 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4382. Min Act: -0.0000

Data Index: 918382 (C4 (Web Text))

Max Activating Token Index: 196