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

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

Neuron 87 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2784. Min Range: -1.2784

Max Act: 1.2784. Min Act: -0.0000

Data Index: 141502 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 1.2784. Min Range: -1.2784

Max Act: 1.2520. Min Act: -0.0000

Data Index: 160515 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 1.2784. Min Range: -1.2784

Max Act: 1.2045. Min Act: -0.0000

Data Index: 1126867 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.9831. Min Act: -0.0000

Data Index: 1353270 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 1.2784. Min Range: -1.2784

Max Act: 1.0079. Min Act: -0.0000

Data Index: 20310 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 1.2784. Min Range: -1.2784

Max Act: 1.0401. Min Act: -0.0000

Data Index: 787694 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.9785. Min Act: -0.0000

Data Index: 1334175 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.9641. Min Act: -0.0000

Data Index: 244005 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.9030. Min Act: -0.0000

Data Index: 296189 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.9446. Min Act: -0.0000

Data Index: 1342159 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.9475. Min Act: -0.0000

Data Index: 1227675 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.8917. Min Act: -0.0000

Data Index: 232926 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.8474. Min Act: -0.0000

Data Index: 203103 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.8480. Min Act: -0.0000

Data Index: 385130 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.8425. Min Act: -0.0000

Data Index: 779006 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.8356. Min Act: -0.0000

Data Index: 460700 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.8564. Min Act: -0.0000

Data Index: 1317268 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.7984. Min Act: -0.0000

Data Index: 179804 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.8219. Min Act: -0.0000

Data Index: 117572 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.7871. Min Act: -0.0000

Data Index: 742088 (C4 (Web Text))

Max Activating Token Index: 268