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

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

Neuron 112 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.7266. Min Act: -0.0000

Data Index: 841843 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.5733. Min Act: -0.0001

Data Index: 63104 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.5296. Min Act: -0.0001

Data Index: 649063 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.5312. Min Act: -0.0000

Data Index: 660027 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.5167. Min Act: -0.0000

Data Index: 199515 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.5372. Min Act: -0.0001

Data Index: 1171051 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1357442 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.4946. Min Act: -0.0001

Data Index: 618664 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.4944. Min Act: -0.0000

Data Index: 267604 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.4938. Min Act: -0.0000

Data Index: 1176680 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.4887. Min Act: -0.0000

Data Index: 83104 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.4931. Min Act: -0.0000

Data Index: 1151190 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.4894. Min Act: -0.0001

Data Index: 416006 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.4820. Min Act: -0.0001

Data Index: 205661 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.4649. Min Act: -0.0000

Data Index: 388250 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.4485. Min Act: -0.0001

Data Index: 149261 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.4599. Min Act: -0.0000

Data Index: 459471 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.4929. Min Act: -0.0001

Data Index: 1011956 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.4759. Min Act: -0.0000

Data Index: 1268545 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.4744. Min Act: -0.0000

Data Index: 337135 (C4 (Web Text))

Max Activating Token Index: 760