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

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

Neuron 3784 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.4020. Min Act: -0.0000

Data Index: 744964 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3742. Min Act: -0.0000

Data Index: 306367 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.4033. Min Act: -0.0000

Data Index: 643641 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3840. Min Act: -0.0000

Data Index: 324519 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3498. Min Act: -0.0000

Data Index: 772076 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3531. Min Act: -0.0000

Data Index: 856935 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3789. Min Act: -0.0000

Data Index: 152292 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3212. Min Act: -0.0000

Data Index: 626415 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3198. Min Act: -0.0000

Data Index: 536517 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3106. Min Act: -0.0000

Data Index: 230605 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3445. Min Act: -0.0000

Data Index: 1232112 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3081. Min Act: -0.0000

Data Index: 652086 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3142. Min Act: -0.0000

Data Index: 846007 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3203. Min Act: -0.0000

Data Index: 377793 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3037. Min Act: -0.0000

Data Index: 894758 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.2966. Min Act: -0.0000

Data Index: 195323 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3186. Min Act: -0.0000

Data Index: 928369 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.2977. Min Act: -0.0000

Data Index: 390432 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3192. Min Act: -0.0000

Data Index: 578025 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.2977. Min Act: -0.0000

Data Index: 1068868 (C4 (Web Text))

Max Activating Token Index: 261