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

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

Neuron 4897 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: 3.0221. Min Range: -3.0221

Max Act: 3.0221. Min Act: -0.0000

Data Index: 786368 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.7485. Min Act: -0.0000

Data Index: 1336589 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.5124. Min Act: -0.0001

Data Index: 1159734 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.2935. Min Act: -0.0001

Data Index: 236684 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.4217. Min Act: -0.0000

Data Index: 964755 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.4573. Min Act: -0.0001

Data Index: 1109020 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.2105. Min Act: -0.0001

Data Index: 987752 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.1443. Min Act: -0.0001

Data Index: 1328 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.1197. Min Act: -0.0000

Data Index: 435510 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.1979. Min Act: -0.0000

Data Index: 1134643 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.0763. Min Act: -0.0001

Data Index: 68125 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.0353. Min Act: -0.0001

Data Index: 1107945 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 3.0221. Min Range: -3.0221

Max Act: 1.9023. Min Act: -0.0001

Data Index: 116940 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.0722. Min Act: -0.0001

Data Index: 1026747 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 3.0221. Min Range: -3.0221

Max Act: 1.8648. Min Act: -0.0001

Data Index: 879899 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.0791. Min Act: -0.0001

Data Index: 851124 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.0699. Min Act: -0.0001

Data Index: 493371 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 3.0221. Min Range: -3.0221

Max Act: 1.9402. Min Act: -0.0001

Data Index: 998995 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 3.0221. Min Range: -3.0221

Max Act: 1.9626. Min Act: -0.0000

Data Index: 976145 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 3.0221. Min Range: -3.0221

Max Act: 1.8489. Min Act: -0.0001

Data Index: 578301 (C4 (Web Text))

Max Activating Token Index: 739