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

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

Neuron 4045 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4134. Min Range: -2.4134

Max Act: 2.4134. Min Act: -0.0000

Data Index: 1050040 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 2.4134. Min Range: -2.4134

Max Act: 2.2740. Min Act: -0.0001

Data Index: 801028 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 2.4134. Min Range: -2.4134

Max Act: 1.7424. Min Act: -0.0000

Data Index: 895957 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 2.4134. Min Range: -2.4134

Max Act: 1.7925. Min Act: -0.0001

Data Index: 1312471 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 2.4134. Min Range: -2.4134

Max Act: 1.8946. Min Act: -0.0000

Data Index: 246245 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 2.4134. Min Range: -2.4134

Max Act: 1.7434. Min Act: -0.0000

Data Index: 378228 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 2.4134. Min Range: -2.4134

Max Act: 1.7625. Min Act: -0.0001

Data Index: 1226774 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 2.4134. Min Range: -2.4134

Max Act: 1.6960. Min Act: -0.0001

Data Index: 764132 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 2.4134. Min Range: -2.4134

Max Act: 1.5826. Min Act: -0.0000

Data Index: 52713 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 2.4134. Min Range: -2.4134

Max Act: 1.5659. Min Act: -0.0000

Data Index: 933378 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 2.4134. Min Range: -2.4134

Max Act: 1.6600. Min Act: -0.0000

Data Index: 673990 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 2.4134. Min Range: -2.4134

Max Act: 1.7435. Min Act: -0.0001

Data Index: 143942 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 2.4134. Min Range: -2.4134

Max Act: 1.5907. Min Act: -0.0000

Data Index: 525012 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 2.4134. Min Range: -2.4134

Max Act: 1.6060. Min Act: -0.0001

Data Index: 1105351 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 2.4134. Min Range: -2.4134

Max Act: 1.5986. Min Act: -0.0000

Data Index: 395751 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 2.4134. Min Range: -2.4134

Max Act: 1.6334. Min Act: -0.0000

Data Index: 708248 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 2.4134. Min Range: -2.4134

Max Act: 1.4885. Min Act: -0.0000

Data Index: 323961 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 2.4134. Min Range: -2.4134

Max Act: 1.5472. Min Act: -0.0001

Data Index: 1109185 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 2.4134. Min Range: -2.4134

Max Act: 1.5453. Min Act: -0.0001

Data Index: 1044436 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 2.4134. Min Range: -2.4134

Max Act: 1.5161. Min Act: -0.0000

Data Index: 828012 (C4 (Web Text))

Max Activating Token Index: 322