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

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

Neuron 2591 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.9198. Min Act: -0.0001

Data Index: 966696 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.8426. Min Act: -0.0001

Data Index: 922928 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.8472. Min Act: -0.0001

Data Index: 520627 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.8619. Min Act: -0.0001

Data Index: 746102 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.8679. Min Act: -0.0001

Data Index: 899406 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.8114. Min Act: -0.0001

Data Index: 741549 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.7882. Min Act: -0.0001

Data Index: 776236 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.8318. Min Act: -0.0001

Data Index: 807813 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.8052. Min Act: -0.0001

Data Index: 1060520 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.8552. Min Act: -0.0001

Data Index: 170742 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.7507. Min Act: -0.0001

Data Index: 1191750 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.7522. Min Act: -0.0001

Data Index: 235095 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.7709. Min Act: -0.0001

Data Index: 1291179 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.7876. Min Act: -0.0001

Data Index: 746680 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.8060. Min Act: -0.0001

Data Index: 1335964 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.7781. Min Act: -0.0001

Data Index: 1066985 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.7720. Min Act: -0.0001

Data Index: 149244 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.7608. Min Act: -0.0001

Data Index: 332 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.7365. Min Act: -0.0001

Data Index: 1294746 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.7142. Min Act: -0.0001

Data Index: 333131 (C4 (Web Text))

Max Activating Token Index: 560