Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 315 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0046. Min Act: -0.0005

Data Index: 1154926 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0046. Min Act: -0.0005

Data Index: 1305916 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0044. Min Act: -0.0005

Data Index: 343955 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0044. Min Act: -0.0005

Data Index: 1165580 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0042. Min Act: -0.0005

Data Index: 863042 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0041. Min Act: -0.0005

Data Index: 630864 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0041. Min Act: -0.0005

Data Index: 1109939 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0041. Min Act: -0.0005

Data Index: 873398 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0040. Min Act: -0.0005

Data Index: 407807 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0039. Min Act: -0.0005

Data Index: 1283186 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0040. Min Act: -0.0005

Data Index: 936367 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0039. Min Act: -0.0005

Data Index: 74707 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0039. Min Act: -0.0005

Data Index: 945508 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0039. Min Act: -0.0005

Data Index: 17554 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0039. Min Act: -0.0005

Data Index: 996996 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0038. Min Act: -0.0005

Data Index: 940045 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0038. Min Act: -0.0005

Data Index: 753350 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0038. Min Act: -0.0005

Data Index: 1002480 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0038. Min Act: -0.0005

Data Index: 262605 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0038. Min Act: -0.0005

Data Index: 413310 (C4 (Web Text))

Max Activating Token Index: 230