Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1117 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.2986. Min Range: -2.2986

Max Act: 2.2986. Min Act: -0.0001

Data Index: 341246 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.5737. Min Act: -0.0001

Data Index: 1205538 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.7533. Min Act: -0.0001

Data Index: 369963 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.6502. Min Act: -0.0001

Data Index: 1051254 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.6255. Min Act: -0.0001

Data Index: 255571 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.7830. Min Act: -0.0001

Data Index: 603087 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.6272. Min Act: -0.0001

Data Index: 625199 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.4407. Min Act: -0.0001

Data Index: 867199 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.5749. Min Act: -0.0001

Data Index: 1127203 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.6323. Min Act: -0.0001

Data Index: 1340019 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.5143. Min Act: -0.0001

Data Index: 343380 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.5008. Min Act: -0.0001

Data Index: 864793 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.5607. Min Act: -0.0001

Data Index: 983660 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.7503. Min Act: -0.0001

Data Index: 970003 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.5613. Min Act: -0.0001

Data Index: 588187 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.4449. Min Act: -0.0001

Data Index: 518099 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.4952. Min Act: -0.0001

Data Index: 675249 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.3893. Min Act: -0.0001

Data Index: 149242 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.5083. Min Act: -0.0001

Data Index: 968394 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.6291. Min Act: -0.0001

Data Index: 1294224 (C4 (Web Text))

Max Activating Token Index: 711