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

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

Neuron 2711 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.5552. Min Act: -0.0002

Data Index: 63234 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.5115. Min Act: -0.0002

Data Index: 659443 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4933. Min Act: -0.0002

Data Index: 1356874 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.5032. Min Act: -0.0002

Data Index: 121038 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4802. Min Act: -0.0002

Data Index: 320603 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4843. Min Act: -0.0001

Data Index: 404125 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4503. Min Act: -0.0001

Data Index: 1004383 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4474. Min Act: -0.0002

Data Index: 1305304 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4202. Min Act: -0.0002

Data Index: 848656 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4336. Min Act: -0.0002

Data Index: 552712 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4513. Min Act: -0.0002

Data Index: 58757 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4297. Min Act: -0.0002

Data Index: 876097 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4439. Min Act: -0.0001

Data Index: 374195 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4286. Min Act: -0.0001

Data Index: 153093 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4165. Min Act: -0.0002

Data Index: 752842 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4373. Min Act: -0.0002

Data Index: 907311 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.3806. Min Act: -0.0001

Data Index: 504170 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4271. Min Act: -0.0002

Data Index: 942058 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4122. Min Act: -0.0002

Data Index: 469750 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.3981. Min Act: -0.0002

Data Index: 273202 (C4 (Web Text))

Max Activating Token Index: 574