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

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

Neuron 1245 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.7071. Min Act: -0.0001

Data Index: 788376 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.6514. Min Act: -0.0000

Data Index: 1121681 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.6217. Min Act: -0.0000

Data Index: 243778 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.6076. Min Act: -0.0000

Data Index: 152507 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5737. Min Act: -0.0001

Data Index: 313670 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5663. Min Act: -0.0001

Data Index: 1269375 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5581. Min Act: -0.0000

Data Index: 910049 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5155. Min Act: -0.0000

Data Index: 507701 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5324. Min Act: -0.0000

Data Index: 310604 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4942. Min Act: -0.0000

Data Index: 417876 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5083. Min Act: -0.0000

Data Index: 1353625 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5174. Min Act: -0.0001

Data Index: 189653 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4998. Min Act: -0.0000

Data Index: 1018516 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4849. Min Act: -0.0001

Data Index: 518735 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4970. Min Act: -0.0000

Data Index: 1065064 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4874. Min Act: -0.0001

Data Index: 1030369 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4858. Min Act: -0.0000

Data Index: 598231 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4712. Min Act: -0.0001

Data Index: 1272886 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4865. Min Act: -0.0000

Data Index: 380914 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4806. Min Act: -0.0000

Data Index: 128613 (C4 (Web Text))

Max Activating Token Index: 869