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

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

Neuron 3838 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: 1.5198. Min Range: -1.5198

Max Act: 1.5198. Min Act: -0.0001

Data Index: 951279 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.4208. Min Act: -0.0001

Data Index: 1168588 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.4675. Min Act: -0.0001

Data Index: 365623 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.4461. Min Act: -0.0001

Data Index: 322581 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.4351. Min Act: -0.0001

Data Index: 591933 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.3701. Min Act: -0.0001

Data Index: 57509 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.2649. Min Act: -0.0001

Data Index: 1560904 (Python Code)

Max Activating Token Index: 916

Text #7

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.3388. Min Act: -0.0001

Data Index: 1450351 (Python Code)

Max Activating Token Index: 108

Text #8

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.2923. Min Act: -0.0001

Data Index: 420170 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.3219. Min Act: -0.0001

Data Index: 976325 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.1490. Min Act: -0.0001

Data Index: 102191 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.2610. Min Act: -0.0001

Data Index: 831183 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.2934. Min Act: -0.0001

Data Index: 124868 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.2760. Min Act: -0.0001

Data Index: 1534327 (Python Code)

Max Activating Token Index: 314

Text #14

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.1613. Min Act: -0.0001

Data Index: 1601955 (Python Code)

Max Activating Token Index: 846

Text #15

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.2000. Min Act: -0.0001

Data Index: 1605134 (Python Code)

Max Activating Token Index: 799

Text #16

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.1714. Min Act: -0.0001

Data Index: 1401090 (Python Code)

Max Activating Token Index: 978

Text #17

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.1792. Min Act: -0.0001

Data Index: 1629215 (Python Code)

Max Activating Token Index: 870

Text #18

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.1698. Min Act: -0.0001

Data Index: 1540820 (Python Code)

Max Activating Token Index: 1003

Text #19

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.3182. Min Act: -0.0001

Data Index: 1143824 (C4 (Web Text))

Max Activating Token Index: 198