Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4064 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.8404. Min Act: -0.0002

Data Index: 1059633 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.7685. Min Act: -0.0002

Data Index: 3036 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.7857. Min Act: -0.0002

Data Index: 1212850 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.7228. Min Act: -0.0002

Data Index: 665898 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.7409. Min Act: -0.0002

Data Index: 509599 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.7628. Min Act: -0.0002

Data Index: 265044 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.7464. Min Act: -0.0002

Data Index: 33888 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.7164. Min Act: -0.0002

Data Index: 1102225 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.7477. Min Act: -0.0002

Data Index: 235965 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.7132. Min Act: -0.0002

Data Index: 846280 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6163. Min Act: -0.0002

Data Index: 676684 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6805. Min Act: -0.0002

Data Index: 85109 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6581. Min Act: -0.0002

Data Index: 949252 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.7132. Min Act: -0.0002

Data Index: 81987 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6299. Min Act: -0.0002

Data Index: 829577 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6095. Min Act: -0.0002

Data Index: 165858 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6546. Min Act: -0.0002

Data Index: 1273353 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6410. Min Act: -0.0002

Data Index: 750481 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6040. Min Act: -0.0002

Data Index: 268019 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6339. Min Act: -0.0002

Data Index: 769348 (C4 (Web Text))

Max Activating Token Index: 96