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

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

Neuron 2275 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1932. Min Range: -1.1932

Max Act: 1.1932. Min Act: -0.0001

Data Index: 1608852 (Python Code)

Max Activating Token Index: 130

Text #1

Max Range: 1.1932. Min Range: -1.1932

Max Act: 1.1903. Min Act: -0.0001

Data Index: 1564875 (Python Code)

Max Activating Token Index: 65

Text #2

Max Range: 1.1932. Min Range: -1.1932

Max Act: 1.0034. Min Act: -0.0001

Data Index: 1206451 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 1.1932. Min Range: -1.1932

Max Act: 1.0197. Min Act: -0.0001

Data Index: 383205 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 1.1932. Min Range: -1.1932

Max Act: 1.0555. Min Act: -0.0001

Data Index: 1626201 (Python Code)

Max Activating Token Index: 227

Text #5

Max Range: 1.1932. Min Range: -1.1932

Max Act: 1.0188. Min Act: -0.0001

Data Index: 1034982 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 1.1932. Min Range: -1.1932

Max Act: 0.9853. Min Act: -0.0001

Data Index: 229325 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 1.1932. Min Range: -1.1932

Max Act: 0.8547. Min Act: -0.0001

Data Index: 1644387 (Python Code)

Max Activating Token Index: 680

Text #8

Max Range: 1.1932. Min Range: -1.1932

Max Act: 0.9251. Min Act: -0.0001

Data Index: 1125565 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 1.1932. Min Range: -1.1932

Max Act: 0.8307. Min Act: -0.0001

Data Index: 547562 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 1.1932. Min Range: -1.1932

Max Act: 0.9683. Min Act: -0.0001

Data Index: 1030394 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 1.1932. Min Range: -1.1932

Max Act: 0.9644. Min Act: -0.0001

Data Index: 1447167 (Python Code)

Max Activating Token Index: 4

Text #12

Max Range: 1.1932. Min Range: -1.1932

Max Act: 0.9350. Min Act: -0.0001

Data Index: 59565 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 1.1932. Min Range: -1.1932

Max Act: 0.9264. Min Act: -0.0001

Data Index: 257591 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 1.1932. Min Range: -1.1932

Max Act: 0.8623. Min Act: -0.0001

Data Index: 20328 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 1.1932. Min Range: -1.1932

Max Act: 0.9477. Min Act: -0.0001

Data Index: 1632238 (Python Code)

Max Activating Token Index: 14

Text #16

Max Range: 1.1932. Min Range: -1.1932

Max Act: 0.9145. Min Act: -0.0001

Data Index: 1359870 (Python Code)

Max Activating Token Index: 500

Text #17

Max Range: 1.1932. Min Range: -1.1932

Max Act: 0.9084. Min Act: -0.0001

Data Index: 982324 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 1.1932. Min Range: -1.1932

Max Act: 0.9240. Min Act: -0.0001

Data Index: 1411366 (Python Code)

Max Activating Token Index: 300

Text #19

Max Range: 1.1932. Min Range: -1.1932

Max Act: 0.8938. Min Act: -0.0001

Data Index: 1561754 (Python Code)

Max Activating Token Index: 790