Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 460 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.5988. Min Range: -4.5988

Max Act: 4.5988. Min Act: -0.0000

Data Index: 1022698 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 4.5988. Min Range: -4.5988

Max Act: 4.2107. Min Act: 0.0000

Data Index: 741334 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 4.5988. Min Range: -4.5988

Max Act: 4.4921. Min Act: -0.0000

Data Index: 720894 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 4.5988. Min Range: -4.5988

Max Act: 3.6378. Min Act: 0.0000

Data Index: 1221680 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 4.5988. Min Range: -4.5988

Max Act: 3.5179. Min Act: -0.0000

Data Index: 512358 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 4.5988. Min Range: -4.5988

Max Act: 3.4713. Min Act: -0.0000

Data Index: 105516 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 4.5988. Min Range: -4.5988

Max Act: 3.3439. Min Act: -0.0000

Data Index: 1163768 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 4.5988. Min Range: -4.5988

Max Act: 3.0332. Min Act: -0.0000

Data Index: 234143 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 4.5988. Min Range: -4.5988

Max Act: 2.9547. Min Act: -0.0000

Data Index: 788512 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 4.5988. Min Range: -4.5988

Max Act: 3.2459. Min Act: -0.0000

Data Index: 294945 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 4.5988. Min Range: -4.5988

Max Act: 3.0320. Min Act: -0.0000

Data Index: 421736 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 4.5988. Min Range: -4.5988

Max Act: 3.1458. Min Act: -0.0000

Data Index: 144937 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 4.5988. Min Range: -4.5988

Max Act: 2.9789. Min Act: -0.0000

Data Index: 851915 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 4.5988. Min Range: -4.5988

Max Act: 2.8084. Min Act: -0.0000

Data Index: 147123 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 4.5988. Min Range: -4.5988

Max Act: 2.5580. Min Act: -0.0000

Data Index: 714269 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 4.5988. Min Range: -4.5988

Max Act: 2.7964. Min Act: -0.0000

Data Index: 1287549 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 4.5988. Min Range: -4.5988

Max Act: 2.8844. Min Act: -0.0000

Data Index: 415381 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 4.5988. Min Range: -4.5988

Max Act: 2.8502. Min Act: -0.0000

Data Index: 939289 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 4.5988. Min Range: -4.5988

Max Act: 2.6647. Min Act: -0.0000

Data Index: 1161599 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 4.5988. Min Range: -4.5988

Max Act: 2.9646. Min Act: -0.0000

Data Index: 318508 (C4 (Web Text))

Max Activating Token Index: 248