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

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

Neuron 2585 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.8387. Min Act: -0.0001

Data Index: 690057 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.8314. Min Act: -0.0001

Data Index: 986742 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7903. Min Act: -0.0001

Data Index: 802102 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7586. Min Act: -0.0001

Data Index: 1157085 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7535. Min Act: -0.0001

Data Index: 332525 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7513. Min Act: -0.0001

Data Index: 1159157 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7465. Min Act: -0.0001

Data Index: 586426 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7849. Min Act: -0.0001

Data Index: 447767 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7417. Min Act: -0.0001

Data Index: 150236 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7862. Min Act: -0.0001

Data Index: 748145 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7598. Min Act: -0.0001

Data Index: 549143 (C4 (Web Text))

Max Activating Token Index: 347

Text #11

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7269. Min Act: -0.0001

Data Index: 1250610 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7444. Min Act: -0.0001

Data Index: 51410 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7211. Min Act: -0.0001

Data Index: 812289 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7409. Min Act: -0.0001

Data Index: 829338 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.6992. Min Act: -0.0001

Data Index: 919168 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7387. Min Act: -0.0001

Data Index: 1067406 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7044. Min Act: -0.0001

Data Index: 563363 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7290. Min Act: -0.0001

Data Index: 113863 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.6852. Min Act: -0.0001

Data Index: 827005 (C4 (Web Text))

Max Activating Token Index: 416