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

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

Neuron 5665 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: 1.8835. Min Range: -1.8835

Max Act: 1.8835. Min Act: -0.0000

Data Index: 119587 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 1.8835. Min Range: -1.8835

Max Act: 1.7449. Min Act: -0.0000

Data Index: 1266549 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 1.8835. Min Range: -1.8835

Max Act: 1.7762. Min Act: -0.0000

Data Index: 891859 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 1.8835. Min Range: -1.8835

Max Act: 1.5481. Min Act: -0.0000

Data Index: 256407 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 1.8835. Min Range: -1.8835

Max Act: 1.5344. Min Act: -0.0000

Data Index: 1293292 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 1.8835. Min Range: -1.8835

Max Act: 1.4919. Min Act: -0.0000

Data Index: 331844 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 1.8835. Min Range: -1.8835

Max Act: 1.4259. Min Act: -0.0000

Data Index: 1088377 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 1.8835. Min Range: -1.8835

Max Act: 1.3396. Min Act: -0.0000

Data Index: 232727 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 1.8835. Min Range: -1.8835

Max Act: 1.2815. Min Act: -0.0000

Data Index: 642288 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 1.8835. Min Range: -1.8835

Max Act: 1.3007. Min Act: -0.0000

Data Index: 754643 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 1.8835. Min Range: -1.8835

Max Act: 1.1319. Min Act: -0.0000

Data Index: 762942 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 1.8835. Min Range: -1.8835

Max Act: 1.1931. Min Act: -0.0000

Data Index: 941825 (C4 (Web Text))

Max Activating Token Index: 484

Text #12

Max Range: 1.8835. Min Range: -1.8835

Max Act: 1.2290. Min Act: -0.0000

Data Index: 59099 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 1.8835. Min Range: -1.8835

Max Act: 1.1058. Min Act: -0.0001

Data Index: 649489 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 1.8835. Min Range: -1.8835

Max Act: 1.0933. Min Act: -0.0000

Data Index: 193731 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 1.8835. Min Range: -1.8835

Max Act: 1.0612. Min Act: -0.0000

Data Index: 45432 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 1.8835. Min Range: -1.8835

Max Act: 1.1017. Min Act: -0.0000

Data Index: 393161 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 1.8835. Min Range: -1.8835

Max Act: 1.0407. Min Act: -0.0000

Data Index: 308309 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 1.8835. Min Range: -1.8835

Max Act: 1.0900. Min Act: -0.0001

Data Index: 404428 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 1.8835. Min Range: -1.8835

Max Act: 1.0465. Min Act: -0.0000

Data Index: 911599 (C4 (Web Text))

Max Activating Token Index: 11