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

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

Neuron 426 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.7861. Min Act: -0.0001

Data Index: 1105390 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.7744. Min Act: -0.0001

Data Index: 1199513 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.7434. Min Act: -0.0001

Data Index: 226859 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.7410. Min Act: -0.0001

Data Index: 871558 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.7300. Min Act: -0.0001

Data Index: 1209921 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6964. Min Act: -0.0001

Data Index: 1057451 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6982. Min Act: -0.0001

Data Index: 493110 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.7218. Min Act: -0.0001

Data Index: 1285415 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.7083. Min Act: -0.0001

Data Index: 1025505 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6903. Min Act: -0.0001

Data Index: 864109 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6653. Min Act: -0.0001

Data Index: 939110 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6016. Min Act: -0.0001

Data Index: 1129278 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6230. Min Act: -0.0001

Data Index: 427154 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6276. Min Act: -0.0001

Data Index: 837188 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5501. Min Act: -0.0001

Data Index: 153389 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6082. Min Act: -0.0001

Data Index: 1269669 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5936. Min Act: -0.0001

Data Index: 796152 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6226. Min Act: -0.0001

Data Index: 875434 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6031. Min Act: -0.0001

Data Index: 659503 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5855. Min Act: -0.0001

Data Index: 15836 (C4 (Web Text))

Max Activating Token Index: 695