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

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

Neuron 3123 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.4487. Min Act: -0.0001

Data Index: 124338 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.3752. Min Act: -0.0001

Data Index: 475642 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.3541. Min Act: -0.0001

Data Index: 176550 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.3344. Min Act: -0.0001

Data Index: 1322346 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.3346. Min Act: -0.0001

Data Index: 467033 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.3449. Min Act: -0.0001

Data Index: 485897 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.3489. Min Act: -0.0001

Data Index: 568349 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.3251. Min Act: -0.0001

Data Index: 214955 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.3250. Min Act: -0.0001

Data Index: 77494 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.3218. Min Act: -0.0001

Data Index: 45708 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.3068. Min Act: -0.0001

Data Index: 673652 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.3440. Min Act: -0.0001

Data Index: 1221635 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.3207. Min Act: -0.0001

Data Index: 925182 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.2776. Min Act: -0.0001

Data Index: 770343 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.2956. Min Act: -0.0001

Data Index: 354121 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.3009. Min Act: -0.0001

Data Index: 42994 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.2988. Min Act: -0.0001

Data Index: 135998 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.2980. Min Act: -0.0001

Data Index: 727263 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.2978. Min Act: -0.0001

Data Index: 1076233 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.2914. Min Act: -0.0001

Data Index: 62845 (C4 (Web Text))

Max Activating Token Index: 119