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

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

Neuron 2135 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.5430. Min Act: -0.0003

Data Index: 1295749 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.5177. Min Act: -0.0003

Data Index: 271768 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.5193. Min Act: -0.0003

Data Index: 409716 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.5219. Min Act: -0.0003

Data Index: 213001 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.5123. Min Act: -0.0003

Data Index: 702454 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.5073. Min Act: -0.0003

Data Index: 441429 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4699. Min Act: -0.0003

Data Index: 399834 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.5137. Min Act: -0.0003

Data Index: 1041964 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4796. Min Act: -0.0003

Data Index: 567022 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4897. Min Act: -0.0003

Data Index: 197528 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4731. Min Act: -0.0003

Data Index: 672675 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4711. Min Act: -0.0003

Data Index: 376040 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4587. Min Act: -0.0003

Data Index: 407293 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4893. Min Act: -0.0003

Data Index: 1170831 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4856. Min Act: -0.0003

Data Index: 850354 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4856. Min Act: -0.0003

Data Index: 1186263 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4841. Min Act: -0.0003

Data Index: 518161 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.5003. Min Act: -0.0003

Data Index: 123291 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4661. Min Act: -0.0003

Data Index: 737567 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4215. Min Act: -0.0003

Data Index: 294715 (C4 (Web Text))

Max Activating Token Index: 892