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

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

Neuron 1591 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: 0.3552. Min Range: -0.3552

Max Act: 0.3477. Min Act: -0.0001

Data Index: 297494 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3298. Min Act: -0.0001

Data Index: 154294 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3303. Min Act: -0.0001

Data Index: 1293020 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3333. Min Act: -0.0001

Data Index: 220876 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3552. Min Act: -0.0001

Data Index: 416778 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3032. Min Act: -0.0001

Data Index: 1329939 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3095. Min Act: -0.0001

Data Index: 629996 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3179. Min Act: -0.0001

Data Index: 707762 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3135. Min Act: -0.0001

Data Index: 815075 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3131. Min Act: -0.0000

Data Index: 414128 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2942. Min Act: -0.0001

Data Index: 212102 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2999. Min Act: -0.0001

Data Index: 634323 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3121. Min Act: -0.0001

Data Index: 945560 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3119. Min Act: -0.0001

Data Index: 748705 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3032. Min Act: -0.0001

Data Index: 171524 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3076. Min Act: -0.0000

Data Index: 193740 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2806. Min Act: -0.0001

Data Index: 520421 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2527. Min Act: -0.0000

Data Index: 1063407 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2968. Min Act: -0.0001

Data Index: 746033 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2890. Min Act: -0.0000

Data Index: 427281 (C4 (Web Text))

Max Activating Token Index: 954