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

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

Neuron 1967 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: 1.6832. Min Range: -1.6832

Max Act: 1.6832. Min Act: -0.0001

Data Index: 1308651 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.5369. Min Act: -0.0001

Data Index: 631073 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.6056. Min Act: -0.0001

Data Index: 494111 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.4752. Min Act: -0.0001

Data Index: 669464 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.4233. Min Act: -0.0001

Data Index: 527567 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.2976. Min Act: -0.0001

Data Index: 155923 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.3457. Min Act: -0.0001

Data Index: 317218 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.2585. Min Act: -0.0001

Data Index: 785886 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.2690. Min Act: -0.0001

Data Index: 789571 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.2198. Min Act: -0.0001

Data Index: 491670 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.2829. Min Act: -0.0001

Data Index: 255461 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.2228. Min Act: -0.0001

Data Index: 717222 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.2068. Min Act: -0.0001

Data Index: 801946 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.1612. Min Act: -0.0001

Data Index: 363143 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.1587. Min Act: -0.0001

Data Index: 881574 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.1512. Min Act: -0.0001

Data Index: 1025896 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.1040. Min Act: -0.0001

Data Index: 1190132 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.0933. Min Act: -0.0001

Data Index: 653124 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.1201. Min Act: -0.0001

Data Index: 96293 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.1510. Min Act: -0.0001

Data Index: 259339 (C4 (Web Text))

Max Activating Token Index: 317