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

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

Neuron 153 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2972. Min Act: -0.0001

Data Index: 1343941 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2954. Min Act: -0.0001

Data Index: 1515246 (Python Code)

Max Activating Token Index: 759

Text #2

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2857. Min Act: -0.0001

Data Index: 912149 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2712. Min Act: -0.0001

Data Index: 1205453 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2866. Min Act: -0.0001

Data Index: 1571750 (Python Code)

Max Activating Token Index: 340

Text #5

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2767. Min Act: -0.0001

Data Index: 1124048 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2533. Min Act: -0.0001

Data Index: 1095598 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2638. Min Act: -0.0001

Data Index: 381783 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2398. Min Act: -0.0001

Data Index: 1082319 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2371. Min Act: -0.0001

Data Index: 1218751 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2485. Min Act: -0.0001

Data Index: 1136820 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2477. Min Act: -0.0001

Data Index: 199093 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2482. Min Act: -0.0001

Data Index: 959958 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2273. Min Act: -0.0000

Data Index: 903946 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2348. Min Act: -0.0001

Data Index: 872034 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2298. Min Act: -0.0001

Data Index: 236394 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2228. Min Act: -0.0001

Data Index: 876005 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2396. Min Act: -0.0001

Data Index: 1064670 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2310. Min Act: -0.0001

Data Index: 452009 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2329. Min Act: -0.0001

Data Index: 601448 (C4 (Web Text))

Max Activating Token Index: 201