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

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

Neuron 3605 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1309. Min Range: -5.1309

Max Act: 5.1309. Min Act: -0.0001

Data Index: 1304 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 5.1309. Min Range: -5.1309

Max Act: 4.2047. Min Act: -0.0001

Data Index: 980496 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 5.1309. Min Range: -5.1309

Max Act: 4.1287. Min Act: -0.0001

Data Index: 1033170 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 5.1309. Min Range: -5.1309

Max Act: 4.2408. Min Act: -0.0001

Data Index: 8625 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 5.1309. Min Range: -5.1309

Max Act: 3.6550. Min Act: -0.0001

Data Index: 39300 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 5.1309. Min Range: -5.1309

Max Act: 3.6894. Min Act: -0.0001

Data Index: 1061618 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 5.1309. Min Range: -5.1309

Max Act: 3.3953. Min Act: -0.0001

Data Index: 813484 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 5.1309. Min Range: -5.1309

Max Act: 3.2152. Min Act: -0.0001

Data Index: 525782 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 5.1309. Min Range: -5.1309

Max Act: 3.1518. Min Act: -0.0001

Data Index: 1205666 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 5.1309. Min Range: -5.1309

Max Act: 3.1569. Min Act: -0.0001

Data Index: 944528 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 5.1309. Min Range: -5.1309

Max Act: 2.9716. Min Act: -0.0001

Data Index: 161453 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 5.1309. Min Range: -5.1309

Max Act: 2.9493. Min Act: -0.0001

Data Index: 854824 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 5.1309. Min Range: -5.1309

Max Act: 2.9913. Min Act: -0.0001

Data Index: 1137144 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 5.1309. Min Range: -5.1309

Max Act: 2.9685. Min Act: -0.0001

Data Index: 903297 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 5.1309. Min Range: -5.1309

Max Act: 2.8226. Min Act: -0.0001

Data Index: 672507 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 5.1309. Min Range: -5.1309

Max Act: 3.0946. Min Act: -0.0001

Data Index: 1197613 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 5.1309. Min Range: -5.1309

Max Act: 2.8079. Min Act: -0.0001

Data Index: 717793 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 5.1309. Min Range: -5.1309

Max Act: 3.0768. Min Act: -0.0001

Data Index: 434054 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 5.1309. Min Range: -5.1309

Max Act: 2.8970. Min Act: -0.0001

Data Index: 638359 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 5.1309. Min Range: -5.1309

Max Act: 3.0353. Min Act: -0.0001

Data Index: 812451 (C4 (Web Text))

Max Activating Token Index: 43