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

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

Neuron 3171 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3177. Min Range: -1.3177

Max Act: 1.2537. Min Act: -0.0000

Data Index: 301701 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 1.3177. Min Range: -1.3177

Max Act: 1.3177. Min Act: -0.0000

Data Index: 74445 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 1.3177. Min Range: -1.3177

Max Act: 1.0633. Min Act: -0.0000

Data Index: 987842 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 1.3177. Min Range: -1.3177

Max Act: 0.9834. Min Act: -0.0000

Data Index: 476800 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 1.3177. Min Range: -1.3177

Max Act: 0.9388. Min Act: -0.0000

Data Index: 1206541 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 1.3177. Min Range: -1.3177

Max Act: 0.8718. Min Act: -0.0000

Data Index: 1256952 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 1.3177. Min Range: -1.3177

Max Act: 0.8472. Min Act: -0.0000

Data Index: 1234973 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 1.3177. Min Range: -1.3177

Max Act: 0.8039. Min Act: -0.0000

Data Index: 845899 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 1.3177. Min Range: -1.3177

Max Act: 0.7277. Min Act: -0.0000

Data Index: 541810 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 1.3177. Min Range: -1.3177

Max Act: 0.7061. Min Act: -0.0001

Data Index: 684193 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 1.3177. Min Range: -1.3177

Max Act: 0.7097. Min Act: -0.0000

Data Index: 1283081 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 1.3177. Min Range: -1.3177

Max Act: 0.7876. Min Act: -0.0001

Data Index: 97074 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 1.3177. Min Range: -1.3177

Max Act: 0.7422. Min Act: -0.0000

Data Index: 793223 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 1.3177. Min Range: -1.3177

Max Act: 0.7380. Min Act: -0.0000

Data Index: 353255 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 1.3177. Min Range: -1.3177

Max Act: 0.7602. Min Act: -0.0000

Data Index: 87027 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 1.3177. Min Range: -1.3177

Max Act: 0.6851. Min Act: -0.0000

Data Index: 228597 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 1.3177. Min Range: -1.3177

Max Act: 0.6831. Min Act: -0.0001

Data Index: 9586 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 1.3177. Min Range: -1.3177

Max Act: 0.5995. Min Act: -0.0000

Data Index: 1067964 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 1.3177. Min Range: -1.3177

Max Act: 0.6442. Min Act: -0.0000

Data Index: 1287183 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 1.3177. Min Range: -1.3177

Max Act: 0.7062. Min Act: -0.0000

Data Index: 1063419 (C4 (Web Text))

Max Activating Token Index: 734