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

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

Neuron 2489 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0564. Min Act: -0.0001

Data Index: 168998 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0601. Min Act: -0.0001

Data Index: 1399101 (Python Code)

Max Activating Token Index: 444

Text #2

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0508. Min Act: -0.0001

Data Index: 274082 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0541. Min Act: -0.0001

Data Index: 240021 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0486. Min Act: -0.0001

Data Index: 1239643 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0593. Min Act: -0.0001

Data Index: 727791 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0473. Min Act: -0.0001

Data Index: 1648698 (Python Code)

Max Activating Token Index: 69

Text #7

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0475. Min Act: -0.0001

Data Index: 1449403 (Python Code)

Max Activating Token Index: 767

Text #8

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0488. Min Act: -0.0001

Data Index: 1638512 (Python Code)

Max Activating Token Index: 88

Text #9

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0468. Min Act: -0.0001

Data Index: 898329 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0445. Min Act: -0.0002

Data Index: 312773 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0428. Min Act: -0.0001

Data Index: 1310381 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0405. Min Act: -0.0001

Data Index: 1233337 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0437. Min Act: -0.0001

Data Index: 1487516 (Python Code)

Max Activating Token Index: 62

Text #14

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0428. Min Act: -0.0001

Data Index: 970229 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0402. Min Act: -0.0001

Data Index: 561434 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0452. Min Act: -0.0001

Data Index: 19692 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0402. Min Act: -0.0001

Data Index: 1018336 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0468. Min Act: -0.0001

Data Index: 229074 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0343. Min Act: -0.0001

Data Index: 393646 (C4 (Web Text))

Max Activating Token Index: 775