Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1993 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3578. Min Act: -0.0000

Data Index: 318379 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3592. Min Act: -0.0000

Data Index: 1098463 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3628. Min Act: -0.0001

Data Index: 1015607 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3496. Min Act: -0.0001

Data Index: 1101702 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3286. Min Act: -0.0001

Data Index: 17611 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3425. Min Act: -0.0001

Data Index: 770560 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3398. Min Act: -0.0000

Data Index: 578437 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3612. Min Act: -0.0001

Data Index: 1318130 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3530. Min Act: -0.0001

Data Index: 316844 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3261. Min Act: -0.0001

Data Index: 330650 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3577. Min Act: -0.0001

Data Index: 712855 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3283. Min Act: -0.0000

Data Index: 1194530 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3160. Min Act: -0.0000

Data Index: 440129 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3012. Min Act: -0.0001

Data Index: 542823 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.2996. Min Act: -0.0001

Data Index: 640691 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.2940. Min Act: -0.0001

Data Index: 1136532 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3025. Min Act: -0.0001

Data Index: 764117 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3123. Min Act: -0.0001

Data Index: 804288 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.2983. Min Act: -0.0001

Data Index: 1257996 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.2964. Min Act: -0.0000

Data Index: 308138 (C4 (Web Text))

Max Activating Token Index: 828