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

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

Neuron 5357 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9704. Min Range: -2.9704

Max Act: 2.9704. Min Act: -0.0000

Data Index: 515240 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 2.9704. Min Range: -2.9704

Max Act: 2.8845. Min Act: -0.0000

Data Index: 1309079 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 2.9704. Min Range: -2.9704

Max Act: 2.5797. Min Act: -0.0000

Data Index: 1172351 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 2.9704. Min Range: -2.9704

Max Act: 1.9480. Min Act: -0.0000

Data Index: 546999 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 2.9704. Min Range: -2.9704

Max Act: 2.1276. Min Act: -0.0000

Data Index: 1357018 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 2.9704. Min Range: -2.9704

Max Act: 2.2764. Min Act: -0.0000

Data Index: 1252447 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 2.9704. Min Range: -2.9704

Max Act: 2.0099. Min Act: -0.0000

Data Index: 1221224 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 2.9704. Min Range: -2.9704

Max Act: 1.8890. Min Act: -0.0000

Data Index: 1078170 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 2.9704. Min Range: -2.9704

Max Act: 2.0463. Min Act: -0.0000

Data Index: 141805 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 2.9704. Min Range: -2.9704

Max Act: 2.0350. Min Act: -0.0000

Data Index: 719738 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 2.9704. Min Range: -2.9704

Max Act: 2.1354. Min Act: -0.0000

Data Index: 1476800 (Python Code)

Max Activating Token Index: 534

Text #11

Max Range: 2.9704. Min Range: -2.9704

Max Act: 2.0880. Min Act: -0.0001

Data Index: 1110267 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 2.9704. Min Range: -2.9704

Max Act: 1.9672. Min Act: -0.0000

Data Index: 1163939 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 2.9704. Min Range: -2.9704

Max Act: 1.8608. Min Act: -0.0000

Data Index: 1097210 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 2.9704. Min Range: -2.9704

Max Act: 1.8542. Min Act: -0.0000

Data Index: 1210043 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 2.9704. Min Range: -2.9704

Max Act: 1.9452. Min Act: -0.0000

Data Index: 231464 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 2.9704. Min Range: -2.9704

Max Act: 1.8240. Min Act: -0.0000

Data Index: 794360 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 2.9704. Min Range: -2.9704

Max Act: 2.0234. Min Act: -0.0000

Data Index: 958463 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 2.9704. Min Range: -2.9704

Max Act: 1.9227. Min Act: -0.0000

Data Index: 1547040 (Python Code)

Max Activating Token Index: 585

Text #19

Max Range: 2.9704. Min Range: -2.9704

Max Act: 1.8220. Min Act: -0.0000

Data Index: 568329 (C4 (Web Text))

Max Activating Token Index: 235