Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4863 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1784. Min Range: -2.1784

Max Act: 2.1784. Min Act: -0.0000

Data Index: 731263 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 2.1784. Min Range: -2.1784

Max Act: 1.6604. Min Act: -0.0000

Data Index: 652316 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 2.1784. Min Range: -2.1784

Max Act: 1.5916. Min Act: -0.0000

Data Index: 1050087 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 2.1784. Min Range: -2.1784

Max Act: 1.6136. Min Act: -0.0000

Data Index: 897979 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 2.1784. Min Range: -2.1784

Max Act: 1.5207. Min Act: -0.0000

Data Index: 337989 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 2.1784. Min Range: -2.1784

Max Act: 1.6073. Min Act: -0.0000

Data Index: 646709 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 2.1784. Min Range: -2.1784

Max Act: 1.5463. Min Act: -0.0000

Data Index: 284650 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 2.1784. Min Range: -2.1784

Max Act: 1.5328. Min Act: -0.0000

Data Index: 761426 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 2.1784. Min Range: -2.1784

Max Act: 1.3842. Min Act: -0.0000

Data Index: 1589851 (Python Code)

Max Activating Token Index: 77

Text #9

Max Range: 2.1784. Min Range: -2.1784

Max Act: 1.4778. Min Act: -0.0000

Data Index: 1133049 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 2.1784. Min Range: -2.1784

Max Act: 1.5376. Min Act: -0.0000

Data Index: 657534 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 2.1784. Min Range: -2.1784

Max Act: 1.5222. Min Act: -0.0000

Data Index: 1632189 (Python Code)

Max Activating Token Index: 1021

Text #12

Max Range: 2.1784. Min Range: -2.1784

Max Act: 1.4664. Min Act: -0.0000

Data Index: 105693 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 2.1784. Min Range: -2.1784

Max Act: 1.4579. Min Act: -0.0000

Data Index: 14049 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 2.1784. Min Range: -2.1784

Max Act: 1.4816. Min Act: -0.0000

Data Index: 1048074 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 2.1784. Min Range: -2.1784

Max Act: 1.3829. Min Act: -0.0000

Data Index: 1415003 (Python Code)

Max Activating Token Index: 340

Text #16

Max Range: 2.1784. Min Range: -2.1784

Max Act: 1.4123. Min Act: -0.0000

Data Index: 450678 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 2.1784. Min Range: -2.1784

Max Act: 1.4259. Min Act: -0.0000

Data Index: 168449 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 2.1784. Min Range: -2.1784

Max Act: 1.3070. Min Act: -0.0000

Data Index: 411394 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 2.1784. Min Range: -2.1784

Max Act: 1.4200. Min Act: -0.0000

Data Index: 101427 (C4 (Web Text))

Max Activating Token Index: 54