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

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

Neuron 192 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4929. Min Range: -2.4929

Max Act: 2.4929. Min Act: -0.0000

Data Index: 972731 (C4 (Web Text))

Max Activating Token Index: 617

Text #1

Max Range: 2.4929. Min Range: -2.4929

Max Act: 2.3997. Min Act: -0.0000

Data Index: 1090259 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 2.4929. Min Range: -2.4929

Max Act: 2.0612. Min Act: -0.0000

Data Index: 59532 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 2.4929. Min Range: -2.4929

Max Act: 2.1731. Min Act: -0.0000

Data Index: 432327 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 2.4929. Min Range: -2.4929

Max Act: 2.1610. Min Act: -0.0000

Data Index: 525648 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 2.4929. Min Range: -2.4929

Max Act: 2.1060. Min Act: -0.0000

Data Index: 790118 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 2.4929. Min Range: -2.4929

Max Act: 2.2023. Min Act: -0.0000

Data Index: 1058311 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 2.4929. Min Range: -2.4929

Max Act: 2.0325. Min Act: -0.0000

Data Index: 1334251 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 2.4929. Min Range: -2.4929

Max Act: 2.0024. Min Act: -0.0000

Data Index: 679317 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 2.4929. Min Range: -2.4929

Max Act: 1.9579. Min Act: -0.0000

Data Index: 106033 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 2.4929. Min Range: -2.4929

Max Act: 1.9599. Min Act: -0.0000

Data Index: 329429 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 2.4929. Min Range: -2.4929

Max Act: 1.9224. Min Act: -0.0000

Data Index: 154692 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 2.4929. Min Range: -2.4929

Max Act: 1.8069. Min Act: -0.0000

Data Index: 467028 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 2.4929. Min Range: -2.4929

Max Act: 1.9155. Min Act: -0.0000

Data Index: 1333421 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 2.4929. Min Range: -2.4929

Max Act: 1.8932. Min Act: -0.0000

Data Index: 3944 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 2.4929. Min Range: -2.4929

Max Act: 1.9009. Min Act: -0.0000

Data Index: 626211 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 2.4929. Min Range: -2.4929

Max Act: 1.8656. Min Act: -0.0000

Data Index: 441074 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 2.4929. Min Range: -2.4929

Max Act: 1.8893. Min Act: -0.0000

Data Index: 826037 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 2.4929. Min Range: -2.4929

Max Act: 1.7819. Min Act: -0.0000

Data Index: 411191 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 2.4929. Min Range: -2.4929

Max Act: 1.8638. Min Act: -0.0000

Data Index: 791162 (C4 (Web Text))

Max Activating Token Index: 104