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

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

Neuron 73 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.3943. Min Act: -0.0001

Data Index: 1629335 (Python Code)

Max Activating Token Index: 684

Text #1

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2697. Min Act: -0.0001

Data Index: 571334 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2565. Min Act: -0.0001

Data Index: 106561 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2609. Min Act: -0.0001

Data Index: 1337609 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2267. Min Act: -0.0001

Data Index: 1408365 (Python Code)

Max Activating Token Index: 630

Text #5

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2570. Min Act: -0.0001

Data Index: 1364209 (Python Code)

Max Activating Token Index: 587

Text #6

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2506. Min Act: -0.0001

Data Index: 1487112 (Python Code)

Max Activating Token Index: 19

Text #7

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2253. Min Act: -0.0001

Data Index: 928886 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2424. Min Act: -0.0001

Data Index: 1274204 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2444. Min Act: -0.0001

Data Index: 944789 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2484. Min Act: -0.0001

Data Index: 659031 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2452. Min Act: -0.0001

Data Index: 1373545 (Python Code)

Max Activating Token Index: 76

Text #12

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2352. Min Act: -0.0001

Data Index: 810880 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2316. Min Act: -0.0001

Data Index: 1453734 (Python Code)

Max Activating Token Index: 228

Text #14

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2304. Min Act: -0.0001

Data Index: 720753 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2314. Min Act: -0.0001

Data Index: 673198 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2197. Min Act: -0.0001

Data Index: 1083369 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2092. Min Act: -0.0001

Data Index: 723496 (C4 (Web Text))

Max Activating Token Index: 547

Text #18

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2214. Min Act: -0.0001

Data Index: 1586385 (Python Code)

Max Activating Token Index: 634

Text #19

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2289. Min Act: -0.0001

Data Index: 1532765 (Python Code)

Max Activating Token Index: 47