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

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

Neuron 6067 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0184. Min Range: -4.0184

Max Act: 4.0184. Min Act: -0.0000

Data Index: 1100947 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 4.0184. Min Range: -4.0184

Max Act: 3.8467. Min Act: -0.0000

Data Index: 87295 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 4.0184. Min Range: -4.0184

Max Act: 3.3806. Min Act: -0.0000

Data Index: 1161184 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 4.0184. Min Range: -4.0184

Max Act: 3.3382. Min Act: -0.0000

Data Index: 1026568 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 4.0184. Min Range: -4.0184

Max Act: 3.1764. Min Act: -0.0000

Data Index: 175920 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 4.0184. Min Range: -4.0184

Max Act: 3.2095. Min Act: -0.0000

Data Index: 784051 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 4.0184. Min Range: -4.0184

Max Act: 3.2910. Min Act: -0.0000

Data Index: 255517 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 4.0184. Min Range: -4.0184

Max Act: 3.0277. Min Act: -0.0000

Data Index: 1286407 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 4.0184. Min Range: -4.0184

Max Act: 2.8868. Min Act: -0.0000

Data Index: 1031953 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 4.0184. Min Range: -4.0184

Max Act: 2.9913. Min Act: -0.0000

Data Index: 777472 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 4.0184. Min Range: -4.0184

Max Act: 2.9815. Min Act: -0.0000

Data Index: 283200 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 4.0184. Min Range: -4.0184

Max Act: 2.9516. Min Act: -0.0000

Data Index: 1088666 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 4.0184. Min Range: -4.0184

Max Act: 2.9284. Min Act: -0.0000

Data Index: 1110845 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 4.0184. Min Range: -4.0184

Max Act: 2.7265. Min Act: -0.0000

Data Index: 721123 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 4.0184. Min Range: -4.0184

Max Act: 2.6916. Min Act: -0.0000

Data Index: 418808 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 4.0184. Min Range: -4.0184

Max Act: 2.6435. Min Act: -0.0000

Data Index: 869292 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 4.0184. Min Range: -4.0184

Max Act: 2.6198. Min Act: -0.0000

Data Index: 535442 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 4.0184. Min Range: -4.0184

Max Act: 2.6355. Min Act: -0.0000

Data Index: 41316 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 4.0184. Min Range: -4.0184

Max Act: 2.7280. Min Act: -0.0000

Data Index: 1014408 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 4.0184. Min Range: -4.0184

Max Act: 2.8235. Min Act: -0.0000

Data Index: 208654 (C4 (Web Text))

Max Activating Token Index: 37