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

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

Neuron 4082 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2941. Min Range: -4.2941

Max Act: 4.2941. Min Act: -0.0000

Data Index: 613785 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 4.2941. Min Range: -4.2941

Max Act: 4.1193. Min Act: -0.0000

Data Index: 165861 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 4.2941. Min Range: -4.2941

Max Act: 4.0893. Min Act: -0.0000

Data Index: 1111688 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 4.2941. Min Range: -4.2941

Max Act: 3.7784. Min Act: -0.0000

Data Index: 1160708 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 4.2941. Min Range: -4.2941

Max Act: 3.6522. Min Act: -0.0000

Data Index: 7487 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 4.2941. Min Range: -4.2941

Max Act: 3.5316. Min Act: -0.0000

Data Index: 357725 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 4.2941. Min Range: -4.2941

Max Act: 3.3199. Min Act: -0.0000

Data Index: 628687 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 4.2941. Min Range: -4.2941

Max Act: 3.4807. Min Act: -0.0000

Data Index: 669099 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 4.2941. Min Range: -4.2941

Max Act: 3.4483. Min Act: -0.0000

Data Index: 474235 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 4.2941. Min Range: -4.2941

Max Act: 3.4450. Min Act: -0.0000

Data Index: 455449 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 4.2941. Min Range: -4.2941

Max Act: 3.4258. Min Act: -0.0000

Data Index: 459012 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 4.2941. Min Range: -4.2941

Max Act: 3.5245. Min Act: -0.0000

Data Index: 548669 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 4.2941. Min Range: -4.2941

Max Act: 3.3622. Min Act: -0.0000

Data Index: 614749 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 4.2941. Min Range: -4.2941

Max Act: 3.3502. Min Act: -0.0000

Data Index: 605785 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 4.2941. Min Range: -4.2941

Max Act: 3.3436. Min Act: -0.0000

Data Index: 280827 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 4.2941. Min Range: -4.2941

Max Act: 3.3363. Min Act: -0.0000

Data Index: 953121 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 4.2941. Min Range: -4.2941

Max Act: 3.3367. Min Act: -0.0000

Data Index: 1069487 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 4.2941. Min Range: -4.2941

Max Act: 3.3072. Min Act: -0.0000

Data Index: 1174002 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 4.2941. Min Range: -4.2941

Max Act: 3.2870. Min Act: -0.0000

Data Index: 344536 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 4.2941. Min Range: -4.2941

Max Act: 3.4015. Min Act: -0.0000

Data Index: 935068 (C4 (Web Text))

Max Activating Token Index: 981