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

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

Neuron 4635 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: 3.3076. Min Range: -3.3076

Max Act: 3.3076. Min Act: -0.0000

Data Index: 876475 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 3.3076. Min Range: -3.3076

Max Act: 2.6265. Min Act: -0.0000

Data Index: 1187387 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 3.3076. Min Range: -3.3076

Max Act: 2.5466. Min Act: -0.0000

Data Index: 1178373 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 3.3076. Min Range: -3.3076

Max Act: 2.5472. Min Act: -0.0000

Data Index: 672182 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 3.3076. Min Range: -3.3076

Max Act: 2.2993. Min Act: -0.0000

Data Index: 785586 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 3.3076. Min Range: -3.3076

Max Act: 2.2570. Min Act: -0.0000

Data Index: 500939 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 3.3076. Min Range: -3.3076

Max Act: 2.3170. Min Act: -0.0000

Data Index: 1120255 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 3.3076. Min Range: -3.3076

Max Act: 2.1649. Min Act: -0.0000

Data Index: 1131059 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 3.3076. Min Range: -3.3076

Max Act: 2.2670. Min Act: -0.0000

Data Index: 79996 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 3.3076. Min Range: -3.3076

Max Act: 2.2564. Min Act: -0.0000

Data Index: 420975 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 3.3076. Min Range: -3.3076

Max Act: 2.2388. Min Act: -0.0000

Data Index: 330821 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 3.3076. Min Range: -3.3076

Max Act: 2.1091. Min Act: -0.0000

Data Index: 222457 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 3.3076. Min Range: -3.3076

Max Act: 2.2340. Min Act: -0.0000

Data Index: 663978 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 3.3076. Min Range: -3.3076

Max Act: 2.1924. Min Act: -0.0000

Data Index: 277060 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 3.3076. Min Range: -3.3076

Max Act: 2.3303. Min Act: -0.0000

Data Index: 400461 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 3.3076. Min Range: -3.3076

Max Act: 2.1859. Min Act: -0.0000

Data Index: 651811 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 3.3076. Min Range: -3.3076

Max Act: 2.2803. Min Act: -0.0000

Data Index: 1160604 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 3.3076. Min Range: -3.3076

Max Act: 2.1395. Min Act: -0.0000

Data Index: 66448 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 3.3076. Min Range: -3.3076

Max Act: 2.0947. Min Act: -0.0000

Data Index: 415394 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 3.3076. Min Range: -3.3076

Max Act: 2.1714. Min Act: -0.0000

Data Index: 138319 (C4 (Web Text))

Max Activating Token Index: 883