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

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

Neuron 2160 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.5450. Min Act: -0.0002

Data Index: 440820 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4450. Min Act: -0.0002

Data Index: 1185136 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4271. Min Act: -0.0002

Data Index: 250883 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4094. Min Act: -0.0002

Data Index: 375706 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4270. Min Act: -0.0002

Data Index: 839127 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3779. Min Act: -0.0002

Data Index: 867369 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3630. Min Act: -0.0002

Data Index: 1175764 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3147. Min Act: -0.0002

Data Index: 931983 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3821. Min Act: -0.0002

Data Index: 1309247 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3543. Min Act: -0.0002

Data Index: 94236 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3647. Min Act: -0.0002

Data Index: 509543 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3725. Min Act: -0.0002

Data Index: 172837 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3559. Min Act: -0.0002

Data Index: 626134 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3502. Min Act: -0.0002

Data Index: 364245 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3355. Min Act: -0.0002

Data Index: 443357 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3626. Min Act: -0.0002

Data Index: 565387 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3369. Min Act: -0.0002

Data Index: 637758 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3462. Min Act: -0.0002

Data Index: 157375 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.2983. Min Act: -0.0002

Data Index: 145158 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3347. Min Act: -0.0002

Data Index: 1051151 (C4 (Web Text))

Max Activating Token Index: 548