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

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

Neuron 2906 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: 0.2912. Min Range: -0.2912

Max Act: 0.2912. Min Act: -0.0000

Data Index: 713607 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2820. Min Act: -0.0000

Data Index: 1078024 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2686. Min Act: -0.0000

Data Index: 1051954 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2465. Min Act: -0.0000

Data Index: 38997 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2117. Min Act: -0.0000

Data Index: 1351635 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2258. Min Act: -0.0000

Data Index: 943726 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2350. Min Act: -0.0000

Data Index: 380172 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2084. Min Act: -0.0000

Data Index: 663128 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2145. Min Act: -0.0000

Data Index: 963546 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2131. Min Act: -0.0000

Data Index: 1165354 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2033. Min Act: -0.0000

Data Index: 763353 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2073. Min Act: -0.0000

Data Index: 1263333 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2083. Min Act: -0.0000

Data Index: 846118 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2064. Min Act: -0.0000

Data Index: 524715 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2059. Min Act: -0.0000

Data Index: 19094 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2083. Min Act: -0.0000

Data Index: 1155541 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2005. Min Act: -0.0000

Data Index: 85874 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.1994. Min Act: -0.0000

Data Index: 492939 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.1983. Min Act: -0.0000

Data Index: 924566 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2053. Min Act: -0.0000

Data Index: 997290 (C4 (Web Text))

Max Activating Token Index: 985