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

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

Neuron 2699 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: 2.0233. Min Range: -2.0233

Max Act: 2.0233. Min Act: -0.0001

Data Index: 1197952 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 2.0233. Min Range: -2.0233

Max Act: 2.0196. Min Act: -0.0000

Data Index: 646701 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 2.0233. Min Range: -2.0233

Max Act: 1.9350. Min Act: -0.0001

Data Index: 787809 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 2.0233. Min Range: -2.0233

Max Act: 1.7752. Min Act: -0.0000

Data Index: 471474 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 2.0233. Min Range: -2.0233

Max Act: 1.7405. Min Act: -0.0001

Data Index: 947914 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 2.0233. Min Range: -2.0233

Max Act: 1.8332. Min Act: -0.0001

Data Index: 446798 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 2.0233. Min Range: -2.0233

Max Act: 1.9402. Min Act: -0.0000

Data Index: 19191 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 2.0233. Min Range: -2.0233

Max Act: 1.7647. Min Act: -0.0000

Data Index: 765358 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 2.0233. Min Range: -2.0233

Max Act: 1.8124. Min Act: -0.0001

Data Index: 217637 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 2.0233. Min Range: -2.0233

Max Act: 1.6575. Min Act: -0.0001

Data Index: 1280 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 2.0233. Min Range: -2.0233

Max Act: 1.8108. Min Act: -0.0001

Data Index: 758780 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 2.0233. Min Range: -2.0233

Max Act: 1.7235. Min Act: -0.0001

Data Index: 241928 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 2.0233. Min Range: -2.0233

Max Act: 1.8489. Min Act: -0.0000

Data Index: 302395 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 2.0233. Min Range: -2.0233

Max Act: 1.7503. Min Act: -0.0000

Data Index: 691985 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 2.0233. Min Range: -2.0233

Max Act: 1.6521. Min Act: -0.0001

Data Index: 792551 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 2.0233. Min Range: -2.0233

Max Act: 1.6874. Min Act: -0.0000

Data Index: 1147984 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 2.0233. Min Range: -2.0233

Max Act: 1.7305. Min Act: -0.0000

Data Index: 191218 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 2.0233. Min Range: -2.0233

Max Act: 1.6576. Min Act: -0.0000

Data Index: 430093 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 2.0233. Min Range: -2.0233

Max Act: 1.6018. Min Act: -0.0000

Data Index: 810570 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 2.0233. Min Range: -2.0233

Max Act: 1.6318. Min Act: -0.0000

Data Index: 649765 (C4 (Web Text))

Max Activating Token Index: 840