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

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

Neuron 2288 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.4368. Min Act: -0.0000

Data Index: 1105262 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3824. Min Act: -0.0001

Data Index: 1289850 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3549. Min Act: -0.0001

Data Index: 1263893 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3288. Min Act: -0.0001

Data Index: 841758 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3289. Min Act: -0.0000

Data Index: 33218 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3203. Min Act: -0.0001

Data Index: 94502 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3302. Min Act: -0.0001

Data Index: 565764 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3738. Min Act: -0.0001

Data Index: 1273627 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3029. Min Act: -0.0000

Data Index: 311974 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3459. Min Act: -0.0000

Data Index: 884966 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3346. Min Act: -0.0000

Data Index: 4038 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3489. Min Act: -0.0000

Data Index: 556035 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3363. Min Act: -0.0001

Data Index: 572860 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3123. Min Act: -0.0001

Data Index: 175465 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3055. Min Act: -0.0001

Data Index: 1310116 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.2932. Min Act: -0.0001

Data Index: 12282 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3086. Min Act: -0.0000

Data Index: 617684 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3444. Min Act: -0.0001

Data Index: 1351666 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3170. Min Act: -0.0001

Data Index: 985322 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3036. Min Act: -0.0001

Data Index: 1099143 (C4 (Web Text))

Max Activating Token Index: 48