Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2027 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.3224. Min Act: -0.0001

Data Index: 37164 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2799. Min Act: -0.0001

Data Index: 971298 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2764. Min Act: -0.0001

Data Index: 1199060 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2458. Min Act: -0.0001

Data Index: 88911 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2627. Min Act: -0.0001

Data Index: 127029 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2318. Min Act: -0.0001

Data Index: 303076 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2469. Min Act: -0.0001

Data Index: 900931 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2465. Min Act: -0.0001

Data Index: 107166 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2263. Min Act: -0.0001

Data Index: 127618 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2305. Min Act: -0.0001

Data Index: 256080 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2460. Min Act: -0.0001

Data Index: 597461 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2250. Min Act: -0.0001

Data Index: 557005 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2233. Min Act: -0.0001

Data Index: 1032530 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.1988. Min Act: -0.0001

Data Index: 745212 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2293. Min Act: -0.0001

Data Index: 1219438 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2090. Min Act: -0.0001

Data Index: 1308578 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.1969. Min Act: -0.0001

Data Index: 1309418 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2305. Min Act: -0.0001

Data Index: 582751 (C4 (Web Text))

Max Activating Token Index: 966

Text #18

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2208. Min Act: -0.0001

Data Index: 430039 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2279. Min Act: -0.0001

Data Index: 370615 (C4 (Web Text))

Max Activating Token Index: 523