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

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

Neuron 3827 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.8172. Min Act: -0.0000

Data Index: 1011282 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.6671. Min Act: -0.0000

Data Index: 958596 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.5687. Min Act: -0.0000

Data Index: 69166 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.5907. Min Act: -0.0000

Data Index: 526084 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.6277. Min Act: -0.0000

Data Index: 872111 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.5200. Min Act: -0.0000

Data Index: 1267966 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.2834. Min Act: -0.0000

Data Index: 1349776 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.4327. Min Act: -0.0000

Data Index: 926418 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.2121. Min Act: -0.0000

Data Index: 225152 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.1738. Min Act: -0.0000

Data Index: 992120 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.1649. Min Act: -0.0000

Data Index: 146410 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.1077. Min Act: -0.0000

Data Index: 83908 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.3892. Min Act: -0.0000

Data Index: 938199 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.0176. Min Act: -0.0000

Data Index: 420123 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.1606. Min Act: -0.0000

Data Index: 7860 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.1649. Min Act: -0.0000

Data Index: 18499 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.1541. Min Act: -0.0000

Data Index: 423811 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.3421. Min Act: -0.0000

Data Index: 1163189 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.0521. Min Act: -0.0000

Data Index: 306963 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 5.8172. Min Range: -5.8172

Max Act: 4.8646. Min Act: -0.0000

Data Index: 125510 (C4 (Web Text))

Max Activating Token Index: 664