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

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

Neuron 3466 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5280. Min Range: -2.5280

Max Act: 2.4233. Min Act: -0.0000

Data Index: 1545553 (Python Code)

Max Activating Token Index: 1006

Text #1

Max Range: 2.5280. Min Range: -2.5280

Max Act: 2.5280. Min Act: -0.0000

Data Index: 1578996 (Python Code)

Max Activating Token Index: 784

Text #2

Max Range: 2.5280. Min Range: -2.5280

Max Act: 2.3982. Min Act: -0.0000

Data Index: 1446453 (Python Code)

Max Activating Token Index: 267

Text #3

Max Range: 2.5280. Min Range: -2.5280

Max Act: 2.4750. Min Act: -0.0000

Data Index: 665573 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 2.5280. Min Range: -2.5280

Max Act: 2.3312. Min Act: -0.0000

Data Index: 1468472 (Python Code)

Max Activating Token Index: 13

Text #5

Max Range: 2.5280. Min Range: -2.5280

Max Act: 2.3082. Min Act: -0.0000

Data Index: 1517246 (Python Code)

Max Activating Token Index: 1010

Text #6

Max Range: 2.5280. Min Range: -2.5280

Max Act: 2.4256. Min Act: -0.0000

Data Index: 803753 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 2.5280. Min Range: -2.5280

Max Act: 2.2881. Min Act: -0.0000

Data Index: 879095 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 2.5280. Min Range: -2.5280

Max Act: 2.1666. Min Act: -0.0000

Data Index: 491297 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 2.5280. Min Range: -2.5280

Max Act: 2.2737. Min Act: -0.0000

Data Index: 361674 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 2.5280. Min Range: -2.5280

Max Act: 2.2689. Min Act: -0.0000

Data Index: 1361827 (Python Code)

Max Activating Token Index: 14

Text #11

Max Range: 2.5280. Min Range: -2.5280

Max Act: 2.2330. Min Act: -0.0000

Data Index: 1501361 (Python Code)

Max Activating Token Index: 940

Text #12

Max Range: 2.5280. Min Range: -2.5280

Max Act: 2.2272. Min Act: -0.0000

Data Index: 1397679 (Python Code)

Max Activating Token Index: 15

Text #13

Max Range: 2.5280. Min Range: -2.5280

Max Act: 2.2142. Min Act: -0.0000

Data Index: 1379637 (Python Code)

Max Activating Token Index: 580

Text #14

Max Range: 2.5280. Min Range: -2.5280

Max Act: 2.3002. Min Act: -0.0000

Data Index: 1455219 (Python Code)

Max Activating Token Index: 585

Text #15

Max Range: 2.5280. Min Range: -2.5280

Max Act: 2.0650. Min Act: -0.0000

Data Index: 1379627 (Python Code)

Max Activating Token Index: 204

Text #16

Max Range: 2.5280. Min Range: -2.5280

Max Act: 2.0618. Min Act: -0.0000

Data Index: 1467342 (Python Code)

Max Activating Token Index: 157

Text #17

Max Range: 2.5280. Min Range: -2.5280

Max Act: 2.0624. Min Act: -0.0000

Data Index: 1586696 (Python Code)

Max Activating Token Index: 81

Text #18

Max Range: 2.5280. Min Range: -2.5280

Max Act: 2.1837. Min Act: -0.0000

Data Index: 1380697 (Python Code)

Max Activating Token Index: 443

Text #19

Max Range: 2.5280. Min Range: -2.5280

Max Act: 2.1679. Min Act: -0.0000

Data Index: 1548464 (Python Code)

Max Activating Token Index: 893