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

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

Neuron 4261 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: 0.3951. Min Range: -0.3951

Max Act: 0.3951. Min Act: -0.0000

Data Index: 227993 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.3951. Min Range: -0.3951

Max Act: 0.3336. Min Act: -0.0000

Data Index: 883336 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 0.3951. Min Range: -0.3951

Max Act: 0.3280. Min Act: -0.0000

Data Index: 24450 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.3951. Min Range: -0.3951

Max Act: 0.3635. Min Act: -0.0000

Data Index: 1343265 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 0.3951. Min Range: -0.3951

Max Act: 0.3468. Min Act: -0.0000

Data Index: 397249 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 0.3951. Min Range: -0.3951

Max Act: 0.3255. Min Act: -0.0000

Data Index: 385650 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 0.3951. Min Range: -0.3951

Max Act: 0.3453. Min Act: -0.0000

Data Index: 239478 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 0.3951. Min Range: -0.3951

Max Act: 0.3290. Min Act: -0.0000

Data Index: 137886 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.3951. Min Range: -0.3951

Max Act: 0.3137. Min Act: -0.0000

Data Index: 1241974 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 0.3951. Min Range: -0.3951

Max Act: 0.3212. Min Act: -0.0000

Data Index: 669121 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.3951. Min Range: -0.3951

Max Act: 0.2916. Min Act: -0.0000

Data Index: 1252125 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 0.3951. Min Range: -0.3951

Max Act: 0.3036. Min Act: -0.0000

Data Index: 669082 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 0.3951. Min Range: -0.3951

Max Act: 0.2900. Min Act: -0.0000

Data Index: 307322 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 0.3951. Min Range: -0.3951

Max Act: 0.3016. Min Act: -0.0000

Data Index: 657421 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 0.3951. Min Range: -0.3951

Max Act: 0.2873. Min Act: -0.0000

Data Index: 1119598 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.3951. Min Range: -0.3951

Max Act: 0.2884. Min Act: -0.0000

Data Index: 620473 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 0.3951. Min Range: -0.3951

Max Act: 0.2686. Min Act: -0.0000

Data Index: 17166 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.3951. Min Range: -0.3951

Max Act: 0.2587. Min Act: -0.0000

Data Index: 86744 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 0.3951. Min Range: -0.3951

Max Act: 0.2802. Min Act: -0.0000

Data Index: 866258 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 0.3951. Min Range: -0.3951

Max Act: 0.2475. Min Act: -0.0000

Data Index: 96881 (C4 (Web Text))

Max Activating Token Index: 723